osint-investigation
Warn
Audited by Snyk on Jun 13, 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). High: the skill’s runtime fetchers ingest outsider-authored free text from public web sources—e.g., CourtListener
snippet/case_nameand absolute URLs viascripts/fetch_courtlistener.py→get_json()→ CSV fields, and similarly GDELT articletitleviascripts/fetch_gdelt.py—which then get included in the agent’s LLM context through the produced CSV/JSON evidence chain.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata