agents-md

Pass

Audited by Gen Agent Trust Hub on Jun 17, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill is purely informational and provides templates and guidelines for documentation tasks. It contains no code, scripts, or instructions that interact with the system or network in a dangerous way.
  • [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and summarize external data (test outcomes, findings, and learnings). While this creates a theoretical surface for indirect prompt injection where malicious content in those inputs could influence the agent's summary, the risk is negligible as the skill lacks high-privilege capabilities like code execution or network exfiltration.
  • Ingestion points: Processes 'test outcomes', 'technical findings', and 'new learnings' into document files (SKILL.md).
  • Boundary markers: Not explicitly defined in the instructions.
  • Capability inventory: Limited to file-writing operations within the project documentation structure.
  • Sanitization: None specified, as the primary role is documentation generation.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 17, 2026, 06:39 AM
Security Audit — agent-trust-hub — agents-md