agent-md-refactor

Pass

Audited by Gen Agent Trust Hub on Mar 18, 2026

Risk Level: SAFENO_CODE
Full Analysis
  • [SAFE]: No malicious patterns, obfuscation, or unauthorized data access were detected. The skill provides guidelines for documentation management and does not interact with sensitive system resources.
  • [NO_CODE]: The skill consists entirely of markdown instructions (README.md and SKILL.md) and does not include any scripts, binaries, or external dependencies.
  • [PROMPT_INJECTION]: The skill processes existing documentation files which could potentially contain indirect prompt injections. However, the risk is negligible as the skill is limited to document reorganization.
  • Ingestion points: Reads content from existing agent files like CLAUDE.md or AGENTS.md during the analysis phase.
  • Boundary markers: No explicit delimiters or instructions to ignore embedded commands are included in the prompt logic.
  • Capability inventory: The skill requires file-read access to analyze instructions and file-write access to create organized files in the .claude/ directory.
  • Sanitization: No sanitization or content validation is performed on the input documentation before it is refactored into new files.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 18, 2026, 01:46 AM