skill-arc-reactor
Build new Claude skills from scratch or supercharge existing ones through rigorous evaluation and iterative improvement. Use when the user wants to create, build, improve, evaluate, audit, enhance, benchmark, test, or package a skill. Also trigger for "turn this into a skill", "make this reusable", "I keep repeating this workflow", or references to SKILL.md, skill frontmatter, description optimization, or skill packaging. Do NOT use for general coding tasks, document creation, or other non-skill workflows. Even if the user just says "skill" in the context of Claude capabilities, this is likely the right skill to load.
94
92%
Does it follow best practices?
Impact
Pending
No eval scenarios have been run
Advisory
Suggest reviewing before use
Security
1 medium severity finding. This skill can be installed but you should review these findings before use.
W011: Third-party content exposure detected (indirect prompt injection risk)
What this means
The skill exposes the agent to untrusted, user-generated content from public third-party sources, creating a risk of indirect prompt injection. This includes browsing arbitrary URLs, reading social media posts or forum comments, and analyzing content from unknown websites.
Why it was flagged
Third-party content exposure detected (high risk: 0.80). Yes — the skill's SKILL.md and the included references (notably references/mcp-rules-integration.md and the Create/Research & Design sections) explicitly instruct the agent to fetch and read external MCP documentation, API/CLI docs, and public sources including GitHub issues to inform MCP tool usage and generate rules, meaning untrusted public/user-generated content would be ingested and could materially influence tool selection and actions.
- Repository
- endor-matt/Arc-Reactor-Skill-Evaluator
- Commit
95142b6
- Audited
- Security analysis
Is this your skill?
If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.