code-slimming
Pass
Audited by Gen Agent Trust Hub on Sep 21, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted repository data, including instruction files (e.g., .cursor/rules, AGENTS.md) and source code, which could contain malicious prompts designed to influence agent behavior. 1. Ingestion points: Reads instructions, manifests, and codebase files. 2. Boundary markers: No explicit delimiters or instructions to ignore embedded prompts are defined. 3. Capability inventory: Executes shell commands for git, ripgrep, and validation scripts. 4. Sanitization: No sanitization of ingested content is performed before processing.
- [COMMAND_EXECUTION]: The skill relies on executing shell commands to gather repository metadata and perform structural analysis. Evidence: workflow includes the use of git commands, ripgrep (rg), and various local audit tools such as knip, vulture, and jscpd.
Audit Metadata