skill-sync
Warn
Audited by Snyk on Jul 11, 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). Stage 4.5 (“skill-sync-source-validator”) and Stage 2 (“skill-content-updater” read role) can fetch outsider-authored public web/docs content from SOURCE URLs at runtime and then write the fetched text into
.tmp/scratch/fetched/source-material-YYYYMMDD.md, which the write agent later reads into the LLM context.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata