srgn-cli

Pass

Audited by Gen Agent Trust Hub on Apr 12, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill's installation instructions fetch configuration files from the author's repository on a well-known hosting service.
  • [COMMAND_EXECUTION]: The skill generates shell commands for the srgn utility to perform source code refactoring and analysis.
  • [PROMPT_INJECTION]: The skill possesses an indirect prompt injection surface due to processing untrusted source code. 1. Ingestion points: Source code files read by the srgn tool (as described in SKILL.md). 2. Boundary markers: Advice to use syntax-aware language scopes and anchored regex to limit matching. 3. Capability inventory: File modification via shell execution of the srgn CLI tool (as described in SKILL.md). 4. Sanitization: Relies on user-controlled pattern matching via regex and tree-sitter queries.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 12, 2026, 03:23 PM
Security Audit — agent-trust-hub — srgn-cli