verification-before-completion
Pass
Audited by Gen Agent Trust Hub on Apr 21, 2026
Risk Level: SAFE
Full Analysis
- [COMMAND_EXECUTION]: The skill requires the agent to execute standard development commands such as build, type-check, and test suites to verify task completion.
- [PROMPT_INJECTION]: The skill reads acceptance criteria from external task descriptions which presents a surface for indirect prompt injection. Ingestion point: Linear issue requirements in SKILL.md. Boundary markers: Absent. Capability inventory: Shell execution for build and test commands. Sanitization: Absent. This data ingestion is necessary for the skill's primary function and relies on the agent's core instructions for safety.
Audit Metadata