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/, and src/ 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, and Grep tools.\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 Bash tool 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
Risk Level
SAFE
Analyzed
Apr 8, 2026, 06:28 PM