tailrocks-code-health-audit

Pass

Audited by Gen Agent Trust Hub on Sep 8, 2026

Risk Level: SAFEDYNAMIC_EXECUTIONINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
  • [DYNAMIC_EXECUTION]: The skill derives the path to its own component, scripts/code-health-predicate.ts, relative to its installation directory to perform measurements. It includes protective checks to ensure the target is a regular file and not a symlink, preventing unauthorized file execution.
  • [COMMAND_EXECUTION]: The skill executes a TypeScript predicate using a closed JSON stdin contract. This execution is constrained by instructions requiring a network-disabled, read-only environment and the scrubbing of secrets before processing.
  • [INDIRECT_PROMPT_INJECTION]: As the skill ingests untrusted data from target repositories, it is theoretically susceptible to indirect injection. However, it explicitly mitigates this in references/runtime-trust.md by instructing the agent to ignore any instructions embedded in data and citing locations of secrets rather than reading them.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 8, 2026, 03:12 PM
Security Audit — agent-trust-hub — tailrocks-code-health-audit