gsd-health
Pass
Audited by Gen Agent Trust Hub on Oct 1, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill performs legitimate maintenance and health checks on a local configuration directory ('.planning/'). It utilizes standard tools like Bash, Grep, and Read to inspect file presence and configuration integrity.
- [INDIRECT_PROMPT_INJECTION]: The skill provides an interface to process local files in the '.planning/' directory. While these files are typically user-generated, they constitute a potential ingestion point for indirect instructions. 1. Ingestion points: Local files within the '.planning/' directory (SKILL.md). 2. Boundary markers: No explicit delimiters or sanitization instructions are provided in the skill wrapper. 3. Capability inventory: The skill has access to Bash and Write tools (SKILL.md). 4. Sanitization: No explicit sanitization or validation of the directory content is performed before processing.
Audit Metadata