anfra-setup-repo
Fail
Audited by Snyk on Nov 19, 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 Anfra setup guide, but it has the agent pipe a remote install script from GitHub straight into bash, which is a risky step the user is not shown in detail, though it is user-approved and points to the vendor's own repository.
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (low risk: 0.10). The required workflow runs queries against the user's own connected database (schema and data profile in step 4, a sample query in step 5), so any outsider-submitted free text stored in those tables, such as customer comments, could reach the agent without it selecting a specific item, though the rule treats own-tenant structured data as non-exposure.
Issues (2)
E004
CRITICALPrompt injection detected in skill instructions.
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata