hai-ast-grep

Pass

Audited by Gen Agent Trust Hub on Jun 17, 2026

Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
  • [PROMPT_INJECTION]: The skill exhibits an attack surface for indirect prompt injection as it is designed to ingest and process untrusted source code from the project environment.
  • Ingestion points: The agent reads and analyzes code files (JS, TS, Python, etc.) to generate or apply ast-grep patterns as described in SKILL.md.
  • Boundary markers: The instructions lack explicit delimiters or warnings to disregard potential prompt injection attempts hidden within the code being analyzed (e.g., in code comments).
  • Capability inventory: The skill has the capability to execute shell commands via ast-grep and perform file system writes through batch rewrites (--update-all).
  • Sanitization: There is no evidence of sanitization or filtering of the code content before it influences the agent's logic or rule generation.
  • [COMMAND_EXECUTION]: The skill's core functionality relies on instructing the agent to execute shell commands using the ast-grep CLI for scanning and modifying source code.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 17, 2026, 02:50 AM
Security Audit — agent-trust-hub — hai-ast-grep