skill-seeker
Warn
Audited by Snyk on Mar 10, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 1.00). The skill explicitly runs skill-seekers on a user-supplied source (scripts/create.py and SKILL.md) that accepts URLs or GitHub repos and scrapes public documentation/GitHub sites into SKILL.md which Claude then reads and uses to generate/refine/install skills, so untrusted third‑party content can directly influence agent behavior.
MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).
- Potentially malicious external URL detected (high risk: 0.90). The create.py script runs skill-seekers with a user-supplied --source (e.g., repo shorthand like "facebook/react" or a URL such as https://hono.dev) at runtime, causing external documentation to be fetched and then used to generate SKILL.md content that directly drives the agent's prompts/skill behavior.
Audit Metadata