pitch-the-fix
Fail
Audited by Snyk on Nov 17, 2026
Risk Level: CRITICAL
Full Analysis
CRITICAL E004: Prompt injection detected in skill instructions.
- Potential prompt injection detected (medium risk: 0.30). The skill is a legitimate cold-email drafting tool, but it repeatedly inserts promotion of the author's paid products (boringfunnels, a Skool community) into the agent's output, which is promotion unrelated to the user's task rather than malicious intent.
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (medium risk: 0.30). The required Phase 1 fallback reads the prospect's last ten Google reviews, and Phase 2 quotes them, so customers (outsiders) can post free text into a feed the workflow consumes for the chosen business without the agent selecting a specific item.
Issues (2)
E004
CRITICALPrompt injection detected in skill instructions.
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata