import-skill
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). This workflow clones and copies an outsider-authored skill directory from a runtime-resolved external git source (public GitHub or a user-provided
skills.sh/repo path) into a scratch area, after which that text-backedSKILL.md/supporting files would be eligible to be ingested/processed by the agent’s LLM.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata