c4-architecture-documentation

Pass

Audited by Gen Agent Trust Hub on Jun 24, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSPROMPT_INJECTIONNO_CODE
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill provides links to official security and development policies hosted on GitHub at github.com/Hack23/ISMS-PUBLIC. These serve as informational references for the architecture standards.
  • [PROMPT_INJECTION]: The skill processes untrusted external data by reviewing pull requests and architectural modifications. It lacks explicit instructions for using delimiters or boundary markers to isolate this untrusted content.
  • Ingestion points: Pull request content and architectural documentation files (e.g., ARCHITECTURE.md, DATA_MODEL.md).
  • Boundary markers: Not specified.
  • Capability inventory: Analyzes code changes and provides evaluative feedback or rejections based on defined rules.
  • Sanitization: No sanitization or validation of the input text is mentioned.
  • [NO_CODE]: The skill is comprised of markdown instructions and does not include any executable scripts, binaries, or automated code functions.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 24, 2026, 03:40 PM
Security Audit — agent-trust-hub — c4-architecture-documentation