verification-loop

Pass

Audited by Gen Agent Trust Hub on Apr 6, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill instructs the agent to execute various shell commands to verify the state of a project, including npm run build, pnpm build, npx tsc, pyright, npm run lint, ruff, and npm run test. These are standard development operations.- [PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface (Category 8) by processing and reporting on external data such as build logs, test results, and file contents.
  • Ingestion points: Tool outputs from build systems, linters, test runners, and file contents returned by grep search commands in SKILL.md.
  • Boundary markers: Absent. The skill does not define clear delimiters or provide instructions to the agent to ignore potentially malicious instructions embedded in the logs or files being analyzed.
  • Capability inventory: The skill possesses the capability to execute shell commands across several phases, which could be leveraged if an injection is successful.
  • Sanitization: Absent. The skill passes raw tool output and grep results directly into the agent's context for reporting.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 6, 2026, 04:01 AM
Security Audit — agent-trust-hub — verification-loop