reference-builder
Pass
Audited by Gen Agent Trust Hub on Sep 22, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONNO_CODE
Full Analysis
- [SAFE]: The skill consists entirely of Markdown instructions and templates designed to guide an AI agent in generating technical documentation. No malicious patterns, obfuscation, or unauthorized access attempts were detected.\n- [NO_CODE]: There are no scripts, executables, or external dependencies included with this skill. It operates solely through natural language instructions.\n- [INDIRECT_PROMPT_INJECTION]: The skill instructions an agent to process source code for documentation extraction.\n
- Ingestion points: Source code referenced in the 'Reference Building Process' section of SKILL.md.\n
- Boundary markers: None present in the instructions for delimiting or sanitizing extracted code comments.\n
- Capability inventory: No scripts, subprocess calls, or network operations are defined in this skill; the risk is limited to the agent's base capabilities.\n
- Sanitization: No sanitization, escaping, or validation steps are specified for processing external source code content.
Audit Metadata