review-spec
Pass
Audited by Gen Agent Trust Hub on Jul 29, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill instructs the agent to execute the
harnesscommand-line tool to perform structured reviews of implementation plans using the commandharness run plan-review --plan <path>. This tool is used for the primary purpose of the skill. - [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it ingests and processes external, potentially untrusted specification documents and codebase files.
- Ingestion points: Specification documents and codebase files provided by the user or task environment.
- Boundary markers: Absent. The instructions do not specify delimiters or markers to isolate external data from the agent's instructions.
- Capability inventory: The skill possesses file system read access and the ability to execute the
harnessCLI tool. - Sanitization: Absent. There are no instructions for sanitizing, validating, or filtering the content of the processed documents.
Audit Metadata