scientific-writing
Warn
Audited by Snyk on Aug 17, 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). SKILL.md specifies that the agent’s “Stage 1” uses the separate research-lookup skill to “search for relevant papers” and “extract key findings,” which implies it may fetch outsider-authored literature content, even though this skill file itself contains only writing/formatting instructions.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata