harness-engineering
Warn
Audited by Snyk on Jul 2, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.75). The skill’s REQUIRED runtime workflow is a harness for autonomous loops that uses “durable thread log” files and “source refresh”/“retrieve” steps; those steps commonly ingest outsider-authored free text from external sources (e.g., public web pages or other third-party documents) into the LLM context via the retrieval/scraping pipeline.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata