blog-writer
Warn
Audited by Snyk on Jul 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: 0.75). SKILL.md:35-36 requires reading “the feature description, issue, or PR provided” and inspecting GitHub repos via the
ghCLI, which can include outsider-authored free text (e.g., issue/PR body, comments, or repo content) that the agent would ingest into the LLM context during research.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata