agents-md-sync

Pass

Audited by Gen Agent Trust Hub on May 8, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill utilizes shell commands including 'git diff' and 'gh pr diff' to identify code modifications. These tools are used appropriately for documentation synchronization within a development environment.\n- [PROMPT_INJECTION]: The skill uses highly prescriptive language (e.g., 'MUST recommend', 'Do not soften') to ensure the agent adheres to documentation standards. These instructions are task-specific and are not attempts to override platform safety filters.\n- [PROMPT_INJECTION]: The skill processes untrusted data from repository files and pull request diffs, creating an indirect injection surface.\n
  • Ingestion points: Existing AGENTS.md files and shell output from git/gh commands.\n
  • Boundary markers: No explicit delimiters or boundary markers are defined for the analyzed content.\n
  • Capability inventory: The agent is authorized to read/write files and execute git/gh commands within the repository.\n
  • Sanitization: There is no mention of sanitizing or escaping the content retrieved from the repository before processing.
Audit Metadata
Risk Level
SAFE
Analyzed
May 8, 2026, 10:15 PM