baoyu-comic
Warn
Audited by Snyk on Aug 21, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (medium risk: 0.30). In SKILL.md/workflow.md, the agent ingests outsider-authored source text provided by the user at runtime (via the
/baoyu-comic ... content.md/ “then paste content” path) to generateanalysis.md,storyboard.md, andprompts/*.md, so the LLM reads attacker-controlled free text without forcing any trusted subset selection.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata