ian-xiaohei-illustrations
Pass
Audited by Gen Agent Trust Hub on Oct 5, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill's primary workflow involves ingesting and analyzing external data provided by the user to generate illustration strategies and prompts. This creates a surface where malicious instructions embedded in the source articles or linked content could attempt to influence the agent's behavior.
- Ingestion points: The skill reads user-supplied articles, links, Notion pages, and Markdown files as specified in the 'Understand the article' step of
SKILL.md. - Boundary markers: The instructions lack explicit requirements for using delimiters or 'ignore embedded instructions' warnings when processing the retrieved text.
- Capability inventory: The agent has the capability to generate images (likely via an image generation tool) and write files to the local workspace (under
assets/<article-slug>-illustrations/as specified in step 5 ofSKILL.md). - Sanitization: No sanitization or filtering logic is prescribed for the external content before it is processed for metaphor extraction.
Audit Metadata