better-agent-md

Pass

Audited by Gen Agent Trust Hub on Apr 11, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [SAFE]: The skill is designed for static analysis and improvement of repository-level agent instruction files. It does not perform network operations, install external packages, or execute arbitrary shell commands.
  • [PROMPT_INJECTION]: The skill ingests untrusted data from the repository's instruction files, creating a surface for indirect prompt injection.
  • Ingestion points: Reads user-provided files such as AGENTS.md, AGENT.md, and other repo-specific files as specified in the SKILL.md workflow.
  • Boundary markers: No explicit markers are used to isolate the content of audited files from the agent's internal reasoning.
  • Capability inventory: The skill lacks capabilities for network access, arbitrary code execution (eval/exec), or destructive file system operations.
  • Sanitization: The skill does not perform sanitization on the text read from external files before processing it.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 11, 2026, 03:19 PM