gate-check
Pass
Audited by Gen Agent Trust Hub on Apr 8, 2026
Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [PROMPT_INJECTION]: The skill processes untrusted project data (design documents, source code, and ADRs) to validate phase transitions, creating a potential surface for indirect prompt injection.\n
- Ingestion points: Artifacts in
design/gdd/,docs/architecture/, andsrc/directories read during the validation process.\n - Boundary markers: None identified; the agent evaluates the content of project files directly to verify presence and quality.\n
- Capability inventory: The skill has access to
Bash,Write,Read,Glob, andGreptools.\n - Sanitization: No explicit sanitization of file content is performed, but the skill follows a collaborative protocol requiring user approval for status updates.\n- [COMMAND_EXECUTION]: The skill uses the
Bashtool to execute local test suites and update project status files. This is intended functionality for a development-focused validation skill and is documented in the allowed-tools configuration.
Audit Metadata