blueprint-work-order
Warn
Audited by Snyk on Feb 27, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 1.00). The skill explicitly fetches and parses GitHub issue content using "gh issue view N --json title,body,labels,number", which pulls untrusted, user-generated third-party content (public GitHub issues) that the agent reads and uses to populate work-orders and drive subsequent actions.
MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).
- Potentially malicious external URL detected (high risk: 0.90). The skill runs "gh issue view N --json title,body" (fetching the GitHub issue at https://github.com/.../issues/N) at runtime and injects the issue body into the work-order generation, meaning externally-hosted issue content can directly control the agent's prompts/output.
Audit Metadata