code-complexity-audit

Pass

Audited by Gen Agent Trust Hub on Mar 5, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill instructs the agent to execute various git commands, including git log, git blame, and git merge-base. These commands are used to identify churn-heavy files and attribute design findings to authors within a 100-commit window. These are standard read-only operations for repository auditing.
  • [PROMPT_INJECTION]: The skill has an indirect prompt injection surface due to its core function of reading and interpreting untrusted source code and comments. Ingestion points: Source code and file content are read during Step 2 (Sampling) and Step 3 (Deep Analysis). Boundary markers: The process lacks explicit instructions or delimiters to prevent the agent from executing instructions found within the code comments. Capability inventory: The skill has the capability to execute shell commands (git). Sanitization: No sanitization is performed on the analyzed content before the agent evaluates it for the final report, potentially allowing crafted comments to influence the audit verdict.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 5, 2026, 08:53 AM