code-symbols

Pass

Audited by Gen Agent Trust Hub on Feb 28, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill uses the Bash tool to run ast-grep commands for structural code search and modification.
  • [EXTERNAL_DOWNLOADS]: The documentation references installation of @ast-grep/cli via npm, and ast-grep via brew and cargo, which are well-known and trusted package managers.
  • [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection (Category 8). * Ingestion points: The skill processes source code files across various user-provided directories. * Boundary markers: No delimiters or instructions are used to isolate code from potential instructions within comments or literals. * Capability inventory: Includes Bash for command execution and Edit for file manipulation. * Sanitization: No content validation or sanitization is performed on the files being processed.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 28, 2026, 11:37 AM