ln-623-code-principles-auditor
Pass
Audited by Gen Agent Trust Hub on Apr 24, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill fetches reference materials and audit contracts from the author's public GitHub repository (levnikolaevich/claude-code-skills) when local resources are missing.\n- [COMMAND_EXECUTION]: Uses the Bash tool to execute Grep and Glob patterns for code scanning. It also leverages platform-specific graph tools (mcp__hex-graph) to identify structural patterns and code duplication.\n- [PROMPT_INJECTION]: The skill processes untrusted codebase files (Ingestion points) during the auditing process. It does not explicitly define boundary markers for the ingested content, though it employs a 'Two-Layer Detection' strategy to verify findings. The skill possesses capabilities to read files, execute shell commands, and write reports (Capability inventory: Bash, Read, Write). No specific sanitization of the audited code is performed (Sanitization).
Audit Metadata