Skills
Navigate
skills/ast-grep/agent-skill/ast-grep-outline/Gen Agent Trust Hub

ast-grep-outline

Pass

Audited by Gen Agent Trust Hub on Aug 22, 2026

Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
  • [SAFE]: The skill contains instructions for a legitimate developer tool and lacks malicious scripts or exfiltration logic.
  • [COMMAND_EXECUTION]: The skill demonstrates using ast-grep and git diff for structural analysis, which are standard development tasks.
  • [PROMPT_INJECTION]: Processing external codebases via ast-grep introduces a surface for indirect prompt injection if source files contain instructions for the agent.
  • Ingestion points: Local files and directories analyzed by the ast-grep outline tool.
  • Boundary markers: Instructions do not provide specific delimiters or ignore-instructions for the tool output.
  • Capability inventory: Structural mapping of source code (read-only).
  • Sanitization: No sanitization or escaping of the tool's output is mentioned before it is processed by the agent.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 22, 2026, 10:12 AM
Security Audit — agent-trust-hub — ast-grep-outline