no-skip

Pass

Audited by Gen Agent Trust Hub on Sep 18, 2026

Risk Level: SAFE
Full Analysis
  • [COMMAND_EXECUTION]: The skill executes a local script, scripts/check-skips.sh, as a PreToolUse hook. This script is used solely for content inspection to block specific patterns (.skip(), .only(), etc.) in test files.
  • [DATA_EXPOSURE]: No network access or external data exfiltration patterns were detected. The skill operates entirely on local file content provided via the agent's tool invocation.
  • [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted code content being written by the agent. However, the script only performs passive string matching using grep and does not execute the input content, minimizing technical risk.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 18, 2026, 06:15 PM
Security Audit — agent-trust-hub — no-skip