test
Pass
Audited by Gen Agent Trust Hub on Oct 2, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes potentially untrusted data from user-supplied change descriptions and acceptance criteria, which are then used to guide the execution of project commands.
- Ingestion points: User-provided
argument-hint(change description, acceptance criteria) and the project'sAGENTS.mdfile. - Boundary markers: The skill lacks explicit instructions to ignore or sanitize embedded instructions within the ingested data.
- Capability inventory: The skill is capable of executing arbitrary project commands, linting, and type checks via the shell.
- Sanitization: No sanitization or validation of the input criteria or project commands is performed before execution.
- [COMMAND_EXECUTION]: The skill is explicitly designed to execute shell commands to verify code changes.
- Evidence: Step 3 of the process instructs the agent to "Run relevant automated tests, lint, and type checks with project commands," specifically referencing
npm testin the report template.
Audit Metadata