skills/polarsource/polar/adr-check/Gen Agent Trust Hub

adr-check

Pass

Audited by Gen Agent Trust Hub on Jul 30, 2026

Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill uses git diff and ls commands to retrieve change information and locate ADR files within the local repository. These are standard operations for a development and code-review tool.
  • [INDIRECT_PROMPT_INJECTION]: The skill ingests data from local repository files, including markdown-based ADRs and git diff output (ingestion points: handbook/engineering/decisions/ files and git diff output). While there are no explicit boundary markers or sanitization steps mentioned for these inputs, the skill's capabilities are restricted to identifying architecture violations and reporting them, which poses minimal risk.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 30, 2026, 12:47 PM
Security Audit — agent-trust-hub — adr-check