internal-comms

Pass

Audited by Gen Agent Trust Hub on Feb 16, 2026

Risk Level: LOW
Full Analysis
  • [Indirect Prompt Injection] (LOW): The skill is designed to ingest and follow instructions from external markdown files located in an 'examples/' directory. While these files are not provided for analysis, the skill's documented behavior is limited to text generation and formatting, which poses a low risk.
  • Ingestion points: Template files referenced in the examples/ directory (e.g., examples/3p-updates.md).
  • Boundary markers: None specified in the instructions.
  • Capability inventory: The skill only assists in text composition and does not possess capabilities for command execution, file system modification (outside of the current context), or network access.
  • Sanitization: The skill does not explicitly define sanitization for the content of the templates it loads.
  • [General Analysis] (SAFE): The skill file (SKILL.md) is purely instructional and lacks any script logic, package dependencies, or obfuscated content. It adheres to standard agent skill structure for organizational guidelines.
Audit Metadata
Risk Level
LOW
Analyzed
Feb 16, 2026, 11:00 AM