increase-average-order-value
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's decisive content is a publisher referral code (
SKILL) that the agent is told to insert into Whop links and into new-business creation, which is disclosed but benefits the publisher in ways the user may not expect, so it is sketchy rather than malicious.
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 feedback, complaints and product pages in the merchant's own store, which outside customers can write into without the agent selecting a specific item first (for example, product reviews and support or feedback forms).
MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).
- Potentially malicious external URL detected (medium risk: 0.30). The decisive inbound dependency is the instructed fetch of the skill catalog's
mainbranch README, which supplies installation commands the agent is directed to use. Its publisher is the skill project's own company-owned repository, which is not a recognized established vendor, so it is treated as common/reputable unofficial rather than strong first-party provenance.
Issues (3)
E004
CRITICALPrompt injection detected in skill instructions.
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
W012
MEDIUMUnverifiable external dependency detected (runtime URL that controls agent).
Audit Metadata