ai-implement
Pass
Audited by Gen Agent Trust Hub on Oct 9, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill instructs the agent to discover and run verification commands, build files, and CI scripts found within the repository. While standard for development tools, this grants the agent the capability to execute arbitrary code defined in the project's environment.
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted external data in the form of specifications and issue tracker tickets.
- Ingestion points: User-provided specifications and issue tracker tickets (
docs/agents/issue-tracker.md). - Boundary markers: The instructions do not define delimiters or specific warnings to ignore instructions embedded within the tickets or specs.
- Capability inventory: The skill allows the agent to read/write files and execute arbitrary shell commands discovered in build/CI configurations.
- Sanitization: There are no explicit instructions for sanitizing or validating the content of the tickets before implementation.
Audit Metadata