deep-research
Fail
Audited by Snyk on Jul 1, 2026
Risk Level: CRITICAL
Full Analysis
CRITICAL E005: Suspicious download URL detected in skill instructions.
- Suspicious download URL detected (high risk: 0.70). The URL is a GitHub repository under an unrecognized username (Socialpranker) rather than an official vendor; while GitHub is a common code host, unknown/low-reputation repos (especially if they publish releases or binaries) are higher risk without further verification.
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.95). At runtime, the workflow’s Phase 4 “Search” fetches web/other external sources and saves them as per-source
sources/NN.md(e.g., public web content via configured search channels), which then get read for Phase 5–6 synthesis into the agent’s LLM context—this is outsider-authored free text from public web content.
Issues (2)
E005
CRITICALSuspicious download URL detected in skill instructions.
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata