release-check
Pass
Audited by Gen Agent Trust Hub on Nov 2, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill permits running local build and check commands found in the repository. It mitigates risk by requiring the agent to inspect scripts for external or destructive side effects before execution and forbidding tool installation or service provisioning.\n- [INDIRECT_PROMPT_INJECTION]: The skill is designed to process external repository data, creating a potential surface for indirect injection.\n
- Ingestion points: Mentions reading repository guidance, specifications, tasks, and CI evidence in
SKILL.md.\n - Boundary markers: The skill contains explicit instructions to treat source content as evidence rather than authority and to maintain bounded scope.\n
- Capability inventory: Includes the ability to execute existing local build/check commands.\n
- Sanitization: Instructions prohibit calling live endpoints, opening secret files, or performing data migrations, and require script inspection prior to execution.
Audit Metadata