c4-diagrams
Pass
Audited by Gen Agent Trust Hub on May 19, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill consists entirely of instructional markdown and architectural templates. It provides a structured workflow for agents to analyze codebases and produce visual documentation without introducing any executable code or risky command patterns.
- [DATA_EXFILTRATION]: While the skill instructs the agent to inspect codebase entry points and integrations, it does not contain any instructions or tools to transmit this data to external or untrusted destinations.
- [PROMPT_INJECTION]: The skill includes a risk of Indirect Prompt Injection (Category 8) because it processes untrusted codebase data during architectural analysis. If a source file contains malicious instructions, the agent might inadvertently follow them.
- Ingestion points: SKILL.md Workflow Step 2 ("inspect entry points, runtime boundaries...") involves reading external file content into the agent's context.
- Boundary markers: The instructions do not define specific delimiters or "ignore instructions in comments" wrappers for the ingested code content.
- Capability inventory: No risky capabilities (like network requests or shell execution) are defined within the skill itself.
- Sanitization: There are no instructions provided to the agent to sanitize or escape content found within the codebase before processing.
Audit Metadata