woostack-status
Pass
Audited by Gen Agent Trust Hub on Sep 22, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes data from external sources including GitHub, Linear, and Plane which could theoretically contain malicious instructions.
- Ingestion points: Data enters the agent's context through GitHub PR metadata, reviews, threads, and external project management artifacts.
- Boundary markers: The instructions explicitly state that artifact content must be treated as "untrusted evidence" and cannot influence repository state or authorize actions.
- Capability inventory: The skill is strictly read-only and lacks the ability to write to the filesystem, perform network POST requests, or execute arbitrary code based on ingested content.
- Sanitization: The skill logic includes strict verification of repository association and identity checks for all external resources.
Audit Metadata