surface-ideas
Warn
Audited by Snyk on Jul 21, 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). SKILL.md instructs the agent to read an externally authored Resource file (from clip-resource / Obsidian Web Clipper / Readwise) at runtime and then derive “question plus motivation” text from it, so outsider-authored free text can be ingested into the LLM context during the “Surface pass.”
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata