ast-grep
Pass
Audited by Gen Agent Trust Hub on Feb 19, 2026
Risk Level: SAFE
Full Analysis
- PROMPT_INJECTION (SAFE): The skill contains instructional content for writing ast-grep rules and does not contain any attempts to override agent behavior or bypass safety filters.
- DATA_EXFILTRATION (SAFE): No hardcoded credentials, sensitive file access patterns, or unauthorized network operations were identified. The tool operates locally on provided codebases.
- COMMAND_EXECUTION (SAFE): The skill demonstrates legitimate use of the
ast-grepCLI. While it includes examples of shell commands usingechoand piping, these are standard practices for testing search patterns and do not involve arbitrary or dangerous command execution. - EXTERNAL_DOWNLOADS (SAFE): The skill does not include instructions for downloading external scripts or installing unverifiable packages from untrusted sources.
- OBFUSCATION (SAFE): No evidence of Base64 encoding, zero-width characters, or other obfuscation techniques intended to hide malicious content.
Audit Metadata