research
Warn
Audited by Snyk on Mar 29, 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.md explicitly instructs the agent to run Gemini or WebSearch queries and to read GitHub repositories via the docs-seeker (e.g., "use WebSearch", "execute
gemini ...", "When you found a potential Github repository URL, usedocs-seeker"), meaning the agent will ingest and act on untrusted public web/user-generated content that can influence its decisions.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata