reference-pack
Warn
Audited by Snyk on Jul 24, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.70). The skill’s required workflow routes the user query to this skill and then reads the markdown body of
skills/<name>/SKILL.md(the in-context instruction set); this is potentially outsider-authored free text because it is authored by the third-party skillpack publisher and ingested at runtime, even though this repo’s own bundled SKILL.md is an example.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata