prepare-artifacts
Warn
Audited by Snyk on Jul 7, 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’s required runtime workflow includes “Fetch the venue's CURRENT Call for Artifacts — mandatory, live” (step 1), which implies ingesting free-form text from public web pages into the agent’s LLM context; additionally, the lint/build steps read the user-provided artifact directory, but that is not outsider-authored unless the user included outsider text.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata