style-extract
Pass
Audited by Gen Agent Trust Hub on Apr 11, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill demonstrates a surface for indirect prompt injection as it processes untrusted text retrieved from external documents.
- Ingestion points: Document content is fetched from the Yuque platform using the
yuque_get_doctool in SKILL.md. - Boundary markers: The instructions lack explicit delimiters or instructions for the agent to ignore embedded commands within the analyzed writing samples.
- Capability inventory: The skill is limited to reading and writing documents within the Yuque environment and does not have access to shell commands or arbitrary external network requests.
- Sanitization: No content filtering or validation is performed on the text retrieved from documents before it is processed for style analysis.
Audit Metadata