brand-positioning-audit
Fail
Audited by Snyk on Nov 16, 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 positioning audit with no malicious intent, but its competitor script's header says it "fetches" live competitor data while it actually returns mock placeholders, and it reports the profiles as "built," which hides that limitation from the user.
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (low risk: 0.10). The required workflow fetches an arbitrary user-supplied brand website (and, in competitor benchmark mode, a named competitor's site) and reads its outsider-influenced copy, but the agent must actively fetch these pages, so an attacker can publish poison without being able to force delivery into the workflow.
Issues (2)
E004
CRITICALPrompt injection detected in skill instructions.
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata