mutation-testing
Pass
Audited by Gen Agent Trust Hub on Feb 17, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION] (LOW): The skill is vulnerable to indirect prompt injection (Category 8) because it reads and analyzes external repository code.\n
- Ingestion points: Reads code files identified by the
git diffcommand (e.g., .ts, .js, .vue files).\n - Boundary markers: Absent. The skill does not use specific delimiters or instructions to prevent the agent from following directions found within the code files it reads.\n
- Capability inventory: The skill allows the agent to read and modify local files and execute shell commands (
pnpm test).\n - Sanitization: Absent. Code content is processed directly without validation or escaping.\n- [COMMAND_EXECUTION] (SAFE): The skill uses
gitandpnpmto identify targets and run test suites. These operations are essential to the primary purpose of mutation testing and are restricted to the local development environment without signs of privilege escalation.
Audit Metadata