maintain-verification-skill
Pass
Audited by Gen Agent Trust Hub on Sep 11, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted local project data that could potentially contain malicious instructions intended to influence the agent's behavior.
- Ingestion points: The agent is instructed to read
features/README.md, project routes, commands, menus, and public documentation as evidence in the source coverage step. - Boundary markers: The instructions lack explicit boundary markers or directives to the agent to ignore instructions embedded within the processed project files.
- Capability inventory: The skill performs execution of project-local tools (Launch, Doctor, Drive, Evidence, Cleanup) and has the ability to edit files within the verification skill directory.
- Sanitization: There is no mention of sanitizing or validating the contents of the project files before they are processed or used to drive the verification tools.
Audit Metadata