snyk-fix
Complete security remediation workflow. Scans code for vulnerabilities using Snyk, fixes them, validates the fix, and optionally creates a PR. Supports both single-issue and batch mode for multiple vulnerabilities. Use this skill when: - User asks to fix security vulnerabilities - User mentions "snyk fix", "security fix", or "remediate vulnerabilities" - User wants to fix a specific CVE, Snyk ID, or vulnerability type (XSS, SQL injection, path traversal, etc.) - User wants to upgrade a vulnerable dependency - User asks to "fix all" vulnerabilities or "fix all high/critical" issues (batch mode)
What this skill does
# Snyk Fix (All-in-One)
Complete security remediation workflow: Parse → Scan → Analyze → Fix → Validate → Summary → (Optional) PR
**Modes**:
- **Single Mode** (default): Fix one vulnerability type at a time (all instances in same file)
- **Batch Mode**: Fix multiple vulnerabilities in priority order (triggered by "all", "batch", severity filter, or count)
---
## Phase 1: Input Parsing
Parse user input to extract:
- **mode**: Single (default) or Batch
- **scan_type**: `code`, `sca`, or `both` (inferred from context)
- **target_vulnerability**: Specific issue ID, CVE, package name, file, or vuln type
- **target_path**: File or directory (defaults to project root)
- **severity_filter** / **max_fixes**: For batch mode (default max: 20)
### Mode & Scan Type Detection
| Signal | Mode | Scan Type |
|--------|------|-----------|
| "all", severity filter, count ("top 5"), or "batch" | Batch | both |
| Specific vuln ID, single type, file reference, or no batch indicators | Single (default) | — |
| Explicit "code"/"sast"/"static" | — | code |
| Explicit "sca"/"dependency"/"package"/package manager name | — | sca |
| `SNYK-` or `CVE-` ID provided | — | both |
| Vulnerability type (XSS, SQL injection, path traversal, etc.) or file reference | — | code |
| Package name reference | — | sca |
| No hints | — | both (highest priority issue) |
---
## Phase 1B: Batch Mode Planning (Skip if Single Mode)
1. Run both `mcp_snyk_snyk_code_scan` and `mcp_snyk_snyk_sca_scan` on project root.
2. Filter by user-specified severity, type, path, or count.
3. Group by vulnerability type (same ID + file for code; same package for SCA). Sort Critical → High → Medium → Low; within same priority, prefer issues with available fixes.
4. Display fix plan as a numbered table (index, type, severity, target, instance count) with estimated file/package changes. **Wait for user confirmation before proceeding.**
- If user says "adjust": allow plan modification.
5. Execute fixes in order (Phase 3 or 4 per item → Phase 5 validate → track result). On failure: stop if `stop_on_failure=true`, else continue.
6. Proceed to Phase 6B after all attempts.
**Batch limits**: max 20 vulnerabilities, max 15 files modified, max 3 fix attempts per item.
---
## Phase 2: Discovery
### Step 2.1: Run Scan(s)
Invoke scans with the target path. Examples:
```
# Code scan
mcp_snyk_snyk_code_scan:
path: "/absolute/path/to/project" # or subdirectory for targeted scans
# SCA scan
mcp_snyk_snyk_sca_scan:
path: "/absolute/path/to/project" # always project root (manifest location)
```
- Code: `mcp_snyk_snyk_code_scan` on target path
- SCA: `mcp_snyk_snyk_sca_scan` on project root
- Both: run in parallel
### Step 2.2: Select Target
- If user specified: find matching issue. If not found: report and STOP.
- If not specified: select highest priority type using: Critical+exploit > Critical > High+exploit > High > Medium > Low. Prefer issues with available fixes.
### Step 2.3: Group Instances (Code Only)
After selecting vulnerability type, collect ALL instances of that same Snyk ID in the same file. Fix all of them together.
### Step 2.4: Document Target
Display a brief summary: type (Code/SCA), ID, severity, title, and for Code — instance count + file/line table; for SCA — package, fix version, dependency path.
### Step 2.5: Check for Fix Path (SCA Only)
**⚠️ If the scan results do not report any fix version or upgrade path for the selected SCA vulnerability, do NOT proceed to Phase 4.** The agent must not attempt to discover or invent a fix on its own when Snyk has no recommended remediation.
Instead, produce a **No Fix Available Report** and STOP:
```
## No Fix Available
| Vulnerability | [Title] |
|---------------|---------|
| **ID** | [Snyk Issue ID] |
| **Severity** | [Critical / High / Medium / Low] |
| **Package** | [package@current_version] |
| **Dependency Path** | [direct / transitive via X → Y → Z] |
### Why No Fix Was Applied
Snyk does not report a fix version or upgrade path for this vulnerability.
The agent will not attempt to resolve issues where no known fix exists.
### Alternatives to Consider
- Monitor for a future fix release from the package maintainer
- Evaluate replacing the package with a maintained alternative
- Apply a manual workaround if the vulnerability context allows it
- Accept the risk and document in your security policy
```
After producing this report:
- Send `mcp_snyk_snyk_send_feedback` with `fixedExistingIssuesCount: 0`
- Do NOT make any file changes
- STOP
---
## Phase 3: Remediation (Code Vulnerabilities)
### Step 3.1: Understand
Read all vulnerable locations. Identify type (SQL injection, XSS, path traversal, command injection, sensitive data exposure, hardcoded secrets, crypto issues, etc.). Review Snyk's remediation guidance.
### Step 3.2: Plan
Document: vulnerability type, root cause, fix approach, security mechanism, instance count.
Common patterns:
- SQL Injection → parameterized queries
- Command Injection → input validation + escaping or avoid shell
- Path Traversal → canonicalize + validate against allowed base
- XSS → output encoding/sanitization for context
- Hardcoded Secrets → move to env vars / secrets manager
### Step 3.3: Apply Fix to ALL Instances
- Fix from bottom to top of file (avoid line number shifts)
- Minimal change; use standard library/framework security features
- Create shared helper if 3+ instances share identical fix pattern
- Add security-relevant comments where non-obvious
- Do NOT refactor unrelated code or change business logic
---
## Phase 4: Remediation (SCA Vulnerabilities)
**Skip to Phase 5 if this is a Code vulnerability (already handled in Phase 3).**
### Step 4.1: Determine Remediation Strategy
Analyze the dependency path and determine which strategy applies. Exactly one of these three strategies must be selected before proceeding:
**Strategy A — Direct Upgrade**
The vulnerable package is a direct dependency in the project manifest. Upgrade it to a version where the vulnerability is fixed.
**Strategy B — Parent Upgrade**
The vulnerable package is a transitive dependency. A newer version of the direct (parent) dependency pulls in a fixed version of the transitive. Upgrade the parent.
**Strategy C — Transitive Fix**
The vulnerable package is a transitive dependency, but no available version of the parent pulls in a fixed transitive. Resolve the transitive to a fixed version using the lowest-impact mechanism available in the ecosystem.
#### How to choose:
1. Is the vulnerable package declared directly in the project manifest?
- **Yes** → **Strategy A**
- **No** → Continue to step 2
2. Identify the direct dependency (parent) that pulls in the vulnerable transitive. Does any available version of the parent resolve the vulnerable transitive to a fixed version?
- **Yes** → **Strategy B** (upgrade the parent)
- **No** → **Strategy C** (transitive fix)
If the application directly imports or uses the transitive dependency (not just via the parent), note this — it affects breaking change analysis for Strategy C.
Document the chosen strategy:
```
## Remediation Strategy
- **Strategy**: [A: Direct Upgrade | B: Parent Upgrade | C: Transitive Fix]
- **Target package to change**: [package@current → package@target]
- **Parent dependency** (if B/C): [parent@current]
- **Manifest file**: [path to manifest]
```
### Step 4.2: Breaking Change Assessment
**⚠️ ALWAYS run `mcp_snyk_snyk_breakability_check` BEFORE applying any changes.** If the tool is unavailable, errors out, or does not return a LOW/MEDIUM/HIGH risk level, proceed to Step 4.2a.
Call `mcp_snyk_snyk_breakability_check` with the package that will actually change in the manifest:
| Strategy | Check breakability on |
|----------|----------------------|
| A (Direct Upgrade) | The direct dependency being upgraded |
| B (Parent Upgrade) | The parent dependency being upgraded |
| C (Transitive Fix) | The transitive dependency being resolved Related in Backend & APIs
jfrog
IncludedInteract with the JFrog Platform via the JFrog CLI and REST/GraphQL APIs. Use this skill when the user wants to manage Artifactory repositories, upload or download artifacts, manage builds, configure permissions, manage users and groups, work with access tokens, configure JFrog CLI servers, search artifacts, manage properties, set up replication, manage JFrog Projects, run security audits or scans, look up CVE details, query exposures scan results from JFrog Advanced Security, manage release bundles and lifecycle operations, aggregate or export platform data, or perform any JFrog Platform administration task. Also use when the user mentions jf, jfrog, artifactory, xray, distribution, evidence, apptrust, onemodel, graphql, workers, mission control, curation, advanced security, exposures, or any JFrog product name.
cupynumeric-migration-readiness
IncludedPre-migration readiness assessor for porting NumPy to cuPyNumeric. Use BEFORE substantial porting work begins when the user asks whether code will scale on GPU, whether they should migrate to cuPyNumeric, which NumPy patterns transfer cleanly, what must be refactored before porting, or mentions pre-port assessment, scaling analysis, or refactor planning. Inspect the user's source code, look up NumPy usage, cross-reference the cuPyNumeric API support manifest, and distinguish distributed-scaling-friendly patterns from blockers such as unsupported APIs, scalar synchronization, host round-trips, Python/object-heavy control flow, shape/data-dependent branching, and in-place mutation hazards. Produce a verdict of READY, LIGHT REFACTOR, SIGNIFICANT REFACTOR, or NOT RECOMMENDED, with concrete refactor pointers.
alibabacloud-data-agent-skill
IncludedInvoke Alibaba Cloud Apsara Data Agent for Analytics via CLI to perform natural language-driven data analysis on enterprise databases. Data Agent for Analytics is an intelligent data analysis agent developed by Alibaba Cloud Database team for enterprise users. It automatically completes requirement analysis, data understanding, analysis insights, and report generation based on natural language descriptions. This tool supports: discovering data resources (instances/databases/tables) managed in DMS, initiating query or deep analysis sessions, real-time progress tracking, and retrieving analysis conclusions and generated reports. Use this Skill when users need to query databases, analyze data trends, generate data reports, ask questions in natural language, or mention "Data Agent", "data analysis", "database query", "SQL analysis", "data insights".
token-optimizer
IncludedReduce OpenClaw token usage and API costs through smart model routing, heartbeat optimization, budget tracking, and native 2026.2.15 features (session pruning, bootstrap size limits, cache TTL alignment). Use when token costs are high, API rate limits are being hit, or hosting multiple agents at scale. The 4 executable scripts (context_optimizer, model_router, heartbeat_optimizer, token_tracker) are local-only — no network requests, no subprocess calls, no system modifications. Reference files (PROVIDERS.md, config-patches.json) document optional multi-provider strategies that require external API keys and network access if you choose to use them. See SECURITY.md for full breakdown.
resend-cli
IncludedUse this skill when the task is specifically about operating Resend from an AI agent, terminal session, or CI job via the official resend CLI: installing/authenticating the CLI, sending/listing/updating/cancelling emails, batch sends, domains and DNS, webhooks and local listeners, inbound receiving, contacts, topics, segments, broadcasts, templates, API keys, profiles, or debugging Resend CLI/API failures. Trigger on mentions of Resend CLI, `resend`, `resend doctor`, `resend emails send`, `resend domains`, `resend webhooks listen`, `resend emails receiving`, or agent-friendly terminal automation.
alibabacloud-odps-maxframe-coding
IncludedUse this skill for MaxFrame SDK development and documentation navigation on Alibaba Cloud MaxCompute (ODPS). Helps answer MaxFrame API, concept, official example, and supported pandas API questions; create data processing programs; read/write MaxCompute tables; debug jobs (remote or local); and build custom DPE runtime images. Trigger when users mention MaxFrame, MaxCompute with MaxFrame, ODPS table processing, DPE runtime, MaxFrame docs/examples, DataFrame/Tensor operations, or GPU runtime setup. Works for both English and Chinese queries about Alibaba Cloud data processing with MaxFrame.