run-overview
Pass
Audited by Gen Agent Trust Hub on Oct 22, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill executes the
minitestCLI tool to retrieve test run data, verdicts, and status information from the local environment. - [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from external test run results which could be used to influence the agent's behavior.
- Ingestion points: Data returned from
minitest --json run verdictsandminitest --json run statuscommands, including user-defined scenario names and criterion text. - Boundary markers: Absent; the instructions do not implement markers to separate external content from agent instructions.
- Capability inventory: Shell command execution (
minitest) and file system write access (.minitap/reply-mode.json). - Sanitization: Absent; the agent is directed to copy scenario names and criterion text verbatim into the final JSON payload without escaping or validation.
Audit Metadata