tech-research
Warn
Audited by Snyk on Jul 29, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (low risk: 0.10). The skill’s required runtime workflow involves “search for” and “record” information including criticisms/limitations (per SKILL.md steps 3.1–3.5), which implies ingestion of outsider-authored free text from whatever search/web sources the agent fetches and uses to draft references.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata