kstack-review-request
Pass
Audited by Gen Agent Trust Hub on Oct 25, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill uses shell scripts to automate the 'crit' and 'crit-cli' tools. It also executes a Python one-liner to identify an available local network port for the review server.
- [INDIRECT_PROMPT_INJECTION]: The skill processes potentially untrusted external data, creating an indirect prompt injection surface. 1. Ingestion points: Processes PR URLs, validation results, and user comments retrieved from the review tool. 2. Boundary markers: No specific delimiters or 'ignore embedded instructions' warnings are present. 3. Capability inventory: Executes CLI tools ('crit', 'crit-cli'), manages background processes, and performs file system operations via the orchestrated tools. 4. Sanitization: The instructions do not specify sanitization or escaping of external content before interpolation into prompts or commands.
Audit Metadata