skills/bigdra50/skills/review-hotspot/Gen Agent Trust Hub

review-hotspot

Pass

Audited by Gen Agent Trust Hub on Jul 5, 2026

Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill instructs the agent to execute the unilyze command-line tool with specific arguments (hotspot -p <project>) to generate analysis reports.
  • [SAFE]: The skill operates entirely within the local development environment, reading git metadata and writing results to a designated report folder (.unity-review/report/) within the project path.
  • [SAFE]: Indirect Prompt Injection Surface:
  • Ingestion points: Git commit history and source code files processed via the unilyze tool (SKILL.md).
  • Boundary markers: The skill uses a strict Markdown table schema for outputting findings, which restricts the interpretation of ingested data.
  • Capability inventory: Limited to shell command execution for analysis and local file writing for reporting.
  • Sanitization: The analysis focuses on extracting quantitative metrics (churn count and complexity scores), which minimizes the risk of the agent executing instructions embedded in code or commit messages.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 5, 2026, 01:15 PM
Security Audit — agent-trust-hub — review-hotspot