personal-tech-design
Pass
Audited by Gen Agent Trust Hub on Oct 25, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONNO_CODE
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes external data that could potentially contain malicious instructions.
- Ingestion points: External content is retrieved via the
yuque_searchtool in Step 2 and from user inputs in Step 1. - Boundary markers: The skill does not implement specific delimiters to isolate external content during interpolation into the document template.
- Capability inventory: The skill has the ability to search repos, list repos, and create documents on the Yuque platform.
- Sanitization: The primary mitigation is a mandatory human review step (Step 4) where the agent presents the draft to the user for validation before it is saved.
- [NO_CODE]: The skill consists entirely of Markdown instructions and a template file. It does not include any executable scripts, binaries, or complex automation code.
- [SAFE]: All external interactions (searching, listing repositories, and creating documents) are performed using tools specifically designed for the Yuque platform, which is a recognized service. These operations are consistent with the skill's stated purpose of personal document management.
Audit Metadata