skills-manager
Warn
Audited by Snyk on Jun 27, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.85). The required workflow fetches and parses outsider-authored free text from public web content at runtime (e.g.,
curl -s https://raw.githubusercontent.com/heilcheng/awesome-agent-skills/.../README.mdand then extracting fields from that README), which is then ingested into the agent’s LLM context for parsing/normalization.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata