claude-code-skill-development
Warn
Audited by Snyk on Apr 28, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.80). The skill's references (see references/examples.md "Process" and the "Research Skill" example) explicitly tell the agent to "Web search first
- Find documentation, repos, specs" and to "clone repos" and "examine GitHub repos", and SKILL.md requires reading those references, so the skill instructs fetching and interpreting arbitrary public web/GitHub content (untrusted third-party sources) that can influence subsequent tool use and decisions.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata