build
Pass
Audited by Gen Agent Trust Hub on Aug 27, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes external, potentially untrusted content such as repository rules, contracts, and source code to perform sensitive actions like file modification and command execution.
- Ingestion points: SKILL.md (Reads repository rules, the full contract, and relevant source code).
- Boundary markers: Absent; there are no instructions to distinguish between data to be processed and instructions to be ignored within the ingested files.
- Capability inventory: SKILL.md (Perform file writes in 'Implement' step and executes subprocesses in 'Run the focused checks' step).
- Sanitization: Absent; the skill lacks validation or sanitization mechanisms for the external content it ingests.
- [COMMAND_EXECUTION]: The skill is designed to execute shell commands to verify code changes.
- Evidence: SKILL.md ('Run the focused checks named in the brief').
Audit Metadata