secure-dependency-health-check
Helps choose secure, healthy open-source packages by evaluating vulnerability status, maintenance health, popularity, community, and security posture. Use this skill when: - Agent needs to import a new dependency - User asks "which package should I use for X?" - User wants to compare packages (A vs B) - User asks "is this package safe?" - User asks for a "secure alternative" to a package - User mentions "dependency health", "package chooser", or "package security"
What this skill does
# Secure Dependency Health Check
Help developers and AI agents make informed decisions when selecting open-source packages by evaluating security health, vulnerability history, popularity, community, and maintenance status.
**Core Principle**: Choose dependencies wisely to minimize supply chain risk.
---
## Quick Start
When asked to recommend a package:
1. Identify the functional requirement
2. Research candidate packages
3. Run `snyk_package_health_check` on each candidate
4. Compare and recommend the healthiest, most secure option
---
## Phase 1: Understand Requirements
**Goal**: Clarify what the user needs before recommending packages.
### Step 1.1: Identify Candidates
If user provided candidates:
- Note each package name and version (if specified)
- Identify the package ecosystem
If user needs suggestions:
- Search for packages that meet the functional requirement
- Select 2-4 top candidates based on popularity/relevance
---
## Phase 2: Security & Health Analysis
**Goal**: Evaluate each candidate package's security posture and overall health.
### Step 2.1: Run Package Health Check for Each Candidate
For each candidate package, run `snyk_package_health_check` with the package name, version, and ecosystem (`npm`, `pypi`, `maven`, `nuget`, or `golang`). Key fields returned:
- **`overall_rating`**: "Healthy" or "Review recommended" — use as the primary evaluation metric
- **`security`**: vulnerability counts by severity (critical/high/medium/low) and a security rating
- **`maintenance`**: lifecycle status, latest release date, `is_archived` flag, and a maintenance rating ("Healthy", "Sustainable", or "Inactive")
- **`popularity`**: download counts, dependent packages/repos, and a popularity rating
- **`community`**: stargazers count, community file presence, and a rating ("Active" or "Sustainable")
- **`latest_version`**: the most recent published version
- **`recommendation`**: a human-readable summary of the overall assessment
### Step 2.2: Review Tool Results
Surface the following from the tool response for comparison:
- Overall rating ("Healthy" vs "Review recommended")
- Security rating and vulnerability breakdown by severity
- Maintenance rating and lifecycle status (check `is_archived`, `latest_release_published_at`)
- Popularity and community ratings
### Step 2.3: Disqualifiers
**Immediately disqualify packages regardless of overall rating if**:
- Security issues found with critical or high severity vulnerabilities
- Maintenance rating is "Inactive" or package is archived (`is_archived: true`)
- No releases in 3+ years (check `latest_release_published_at`)
- Known malicious package (supply chain attack)
- Typosquatting indicators (similar name to popular package)
---
## Phase 3: Generate Recommendation
**Goal**: Present a clear, actionable comparison.
### Step 3.1: Comparison Table
```
## Package Comparison: [Use Case]
| Criteria | Package A | Package B | Package C |
|----------|-----------|-----------|-----------|
| **Overall Rating** | Healthy | Review recommended | Healthy |
| **Security Rating** | Security issues found | Security issues found | No known security issues |
| **Critical CVEs** | 0 | 1 | 0 |
| **High CVEs** | 1 | 2 | 0 |
| **Maintenance** | Healthy | Inactive | Healthy |
| **Last Release** | 2 weeks ago | 8 months ago | 1 month ago |
| **Downloads** | 500K | 2M | 300K |
| **Popularity** | Influential project | Influential project | Influential project |
### Recommendation: **Package C**
**Reasons**:
1. "Healthy" overall rating with no known security issues
2. Healthy maintenance rating - actively maintained with recent release
3. Fewest vulnerabilities across all severity levels
**Trade-offs**:
- Fewer downloads than Package B (less battle-tested)
- Consider if specific features of Package A/B are required
**Recommended version**: Use the `latest_version` from the tool response to pin an exact version.
```
### Step 3.2: Alternative Scenarios
If no package meets the security threshold:
```
## Warning: No Secure Option Available
All evaluated packages have significant security concerns:
- Package A: 2 Critical CVEs (actively exploited)
- Package B: Abandoned - no updates in 3 years
- Package C: Multiple high-severity vulnerabilities with no fix available
### Alternatives:
1. **Implement in-house**: For simple functionality
2. **Fork and fix**: If one package is close but has fixable issues
3. **Wait**: If updates are expected soon
4. **Accept risk**: With documented justification and monitoring
```
---
## Phase 4: Integration Guidance
**Goal**: Help the user safely add the recommended package.
### Step 4.1: Post-Installation Scan
Recommend running `snyk_sca_scan` after installation to verify the full dependency tree doesn't introduce unexpected vulnerabilities.
### Step 4.2: Monitoring Recommendation
Advise committing lock files, enabling vulnerability notifications, and checking for security updates regularly.
---
## Error Handling
### Package Not Found
- Verify package name and ecosystem
- Check for typos
- Search for alternative names
### Scan Fails or Insufficient Data
- The tool may return "Snyk doesn't have sufficient information about this package" for some packages
- Retry once; if still no data, fall back to manual research
- Report partial results with disclaimer that the tool could not assess this package
### No Candidates Meet Threshold
- Report why each failed
- Suggest alternatives (in-house, fork, wait)
- Document risk if user proceeds anyway
---
## Constraints
1. **Never recommend packages with known exploits**
2. **Always specify exact version** in recommendations
3. **Disclose limitations** if full analysis isn't possible
4. **Update recommendations** if user provides new constraints
Related in AI Agents
skill-development
IncludedComprehensive meta-skill for creating, managing, validating, auditing, and distributing Claude Code skills and slash commands (unified in v2.1.3+). Provides skill templates, creation workflows, validation patterns, audit checklists, naming conventions, YAML frontmatter guidance, progressive disclosure examples, and best practices lookup. Use when creating new skills, validating existing skills, auditing skill quality, understanding skill architecture, needing skill templates, learning about YAML frontmatter requirements, progressive disclosure patterns, tool restrictions (allowed-tools), skill composition, skill naming conventions, troubleshooting skill activation issues, creating custom slash commands, configuring command frontmatter, using command arguments ($ARGUMENTS, $1, $2), bash execution in commands, file references in commands, command namespacing, plugin commands, MCP slash commands, Skill tool configuration, or deciding between skills vs slash commands. Delegates to docs-management skill for official documentation.
reprompter
IncludedTransform messy prompts into well-structured, effective prompts — single or multi-agent. Use when: "reprompt", "reprompt this", "clean up this prompt", "structure my prompt", rough text needing XML tags and best practices, "reprompter teams", "repromptception", "run with quality", "smart run", "smart agents", multi-agent tasks, audits, parallel work, anything going to agent teams. Don't use when: simple Q&A, pure chat, immediate execution-only tasks. See "Don't Use When" section for details. Outputs: Structured XML/Markdown prompt, quality score (before/after), optional team brief + per-agent sub-prompts, agent team output files. Success criteria: Single mode quality score ≥ 7/10; Repromptception per-agent prompt quality score 8+/10; all required sections present, actionable and specific.
adaptive-compaction
IncludedAdaptive add-on policy and recovery layer that decides WHEN to compact, prune, snapshot, or fork -- replacing fixed-percent auto-compaction across Claude Code, Codex, and MCP-capable hosts. Trigger on auto-compact timing or damage: "when should I compact", "is it safe to compact now or start a fresh session", "auto-compact fires too early/mid-task", "switching to an unrelated task but the window still has space", "context rot", "answers get worse the longer the session runs", "the agent forgot the plan or my decisions after it summarized", "add a layer on top that manages context without changing the agent", raising autoCompactWindow to give the policy room, or installing/tuning a cross-tool compaction policy or PreCompact hook -- even when "compaction" is never said but the problem is context-window pressure or post-summarization memory loss. Do NOT use to summarize a conversation, build RAG, write a summarization prompt (decides WHEN not HOW), or answer max-context-length trivia.
agent-skill-creator
IncludedCreate cross-platform agent skills from workflow descriptions. Activates when users ask to create an agent, automate a repetitive workflow, create a custom skill, or need advanced agent creation. Triggers on phrases like create agent for, automate workflow, create skill for, every day I have to, daily I need to, turn process into agent, need to automate, create a cross-platform skill, validate this skill, export this skill, migrate this skill. Supports single skills, multi-agent suites, transcript processing, template-based creation, interactive configuration, cross-platform export, and spec validation.
llm-wiki
IncludedUse when building or maintaining a persistent personal knowledge base (second brain) in Obsidian where an LLM incrementally ingests sources, updates entity/concept pages, maintains cross-references, and keeps a synthesis current. Triggers include "second brain", "Obsidian wiki", "personal knowledge management", "ingest this paper/article/book", "build a research wiki", "compound knowledge", "Memex", or whenever the user wants knowledge to accumulate across sessions instead of being re-derived by RAG on every query.
skill-master
IncludedAgent Skills authoring, evaluation, and optimization. Create, edit, validate, benchmark, and improve skills following the agentskills.io specification. Use when designing SKILL.md files, structuring skill folders (references, scripts, assets), ingesting external documentation into skills, running trigger evals, benchmarking skill quality, optimizing descriptions, or performing blind A/B comparisons. Keywords: agentskills.io, SKILL.md, skill authoring, eval, benchmark, trigger optimization.