skills/edmundmiller/dotfiles/ast-grep/Gen Agent Trust Hub

ast-grep

Pass

Audited by Gen Agent Trust Hub on Jun 21, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill includes a pre-compiled binary library (lib/macos-arm64/libnextflow.dylib) and configures the host tool to load it at runtime via sgconfig.yml. This allows for the execution of binary code bundled with the skill.
  • [PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface by processing untrusted data (source code files) without explicit boundary markers or sanitization, while maintaining file-writing capabilities. 1. Ingestion points: User-provided code files (SKILL.md). 2. Boundary markers: Absent. 3. Capability inventory: File system read and write via the ast-grep tool (SKILL.md). 4. Sanitization: Absent.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 21, 2026, 01:26 PM
Security Audit — agent-trust-hub — ast-grep