ingest

Warn

Audited by Snyk on Jul 7, 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). SKILL.md requires reading the newly appeared file in raw/ completely and extracting key takeaways to create/update multiple wiki pages, so if that raw/ file is outsider-authored free text, it will be ingested into the LLM context via the runtime “read source file in raw/ completely” → “extract key takeaways” path.

Issues (1)

W011
MEDIUM

Third-party content exposure detected (indirect prompt injection risk).

Audit Metadata
Risk Level
MEDIUM
Analyzed
Jul 7, 2026, 04:00 PM
Issues
1
Security Audit — snyk — ingest