agents-md-generator

Pass

Audited by Gen Agent Trust Hub on Feb 17, 2026

Risk Level: SAFENO_CODE
Full Analysis
  • SAFE (SAFE): No security issues or malicious patterns were detected. The skill provides instructional templates for repository documentation and includes proactive warnings against committing sensitive credentials.
  • NO_CODE (SAFE): The skill is entirely prompt-based and does not include any scripts, executable binaries, or external dependency installations.
  • Indirect Prompt Injection (SAFE): While the skill analyzes codebases as an ingestion surface, it lacks any dangerous capabilities to exploit. Ingestion points: Phase 1 Repository Analysis. Boundary markers: Absent. Capability inventory: None (no network access, file-write operations, or shell execution). Sanitization: Absent.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 17, 2026, 06:38 PM