brooks-sweep

Warn

Audited by Gen Agent Trust Hub on Aug 5, 2026

Risk Level: MEDIUMCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill executes various shell commands for environment discovery and fix verification.
  • Evidence: Uses git ls-files and find to enumerate files in the repository during the setup phase in sweep-guide.md (Step 0a).
  • Evidence: Automatically executes project-specific test and lint commands (e.g., package.json scripts, pytest, cargo test, go test) to verify the integrity of applied fixes in sweep-guide.md (Step 2e).
  • [PROMPT_INJECTION]: The skill is vulnerable to indirect prompt injection via the codebase it analyzes.
  • Ingestion points: Reads and processes project source files and configuration (.brooks-lint.yaml) to identify issues and apply remedies (Step 1b, Step 2a).
  • Boundary markers: The skill does not explicitly define markers to prevent the agent from following instructions embedded within the codebase being scanned.
  • Capability inventory: The agent has the authority to modify files (Edit or Write) and execute shell commands based on its analysis.
  • Sanitization: There is no evidence of sanitization or filtering of the codebase content before it is processed by the logic engine.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Aug 5, 2026, 01:49 PM
Security Audit — agent-trust-hub — brooks-sweep