hook-mining
Warn
Audited by Snyk on Aug 23, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (medium risk: 0.30). In the required runtime workflow, hook-mining reads hook text from a user-provided CSV file via
mine_hooks.py(Path(args[0])→csv.DictReader→r.get(hcol)→mine()), so an outsider can supply the free text through that input channel for the agent to process.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata