skills/ulpi-io/skills/ast-grep/Gen Agent Trust Hub

ast-grep

Pass

Audited by Gen Agent Trust Hub on Apr 1, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill provides instructions to install the ast-grep CLI through well-known services including Homebrew, Cargo, and npm (@ast-grep/cli), as well as the official project repository on GitHub.
  • [PROMPT_INJECTION]: The skill processes untrusted local code through structural search, which constitutes a surface for indirect prompt injection.
  • Ingestion points: Local project files searched via ast-grep scan and ast-grep run commands.
  • Boundary markers: Absent for the tool's output; however, the skill mandates a strict six-step verification protocol requiring the agent to test rules individually before production use.
  • Capability inventory: Bash (CLI execution), Read (file access), and Write (file modification).
  • Sanitization: The instructions emphasize the need to escape metavariables ($VAR) in shell commands to ensure command integrity.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 1, 2026, 06:52 PM