local-seo-plan
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's only sales content is a role-gated, once-per-run offer for the author's own services, which is self-serving promotion tied to the task rather than a covert or deceptive attack on the user, but under recall-first it is flagged as possible promotion inserted into the user's deliverable.
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (medium risk: 0.30). The required workflow reads customer-written Google reviews and call-log notes, both of which outsiders can create without the agent selecting a specific item, so this is monitored-feed exposure.
Issues (2)
E004
CRITICALPrompt injection detected in skill instructions.
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata