deep-company-analyser
Warn
Audited by Snyk on Jun 16, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.95). The skill’s required workflow explicitly ingests outsider-authored free text from runtime-fetched public sources (e.g., case studies and G2/Capterra/TrustRadius review pages containing verbatim customer quotes) into the LLM context during “Extract and analyze” (Step 2) and then outputs it (Step 3).
MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).
- Potentially malicious external URL detected (high risk: 0.80). This skill explicitly requests and fetches user-supplied external sources at runtime — e.g., company website URLs, case-studies page URLs, and G2/Capterra review pages described in Step 1 — and ingests that fetched content into the agent context to directly shape prompts and outputs.
Issues (2)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
W012
MEDIUMUnverifiable external dependency detected (runtime URL that controls agent).
Audit Metadata