restructure-help-article
Pass
Audited by Gen Agent Trust Hub on Sep 26, 2026
Risk Level: SAFE
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingests external content from help articles, creating a surface for potential indirect prompt injection. However, the instructions are focused on text formatting and restructuring without providing the agent with capabilities to execute code or perform sensitive operations based on the article content.
- Ingestion points: Help articles provided by the user or fetched from Clueso projects (SKILL.md).
- Boundary markers: None specified.
- Capability inventory: The skill is restricted to text processing and providing links to the user. No high-risk capabilities like shell execution or filesystem writes are exposed to the ingested data.
- Sanitization: No explicit sanitization or filtering is defined for the input text.
- [EXTERNAL_DOWNLOADS]: The instructions guide the agent to help the user install the Clueso MCP server from
https://connect.clueso.io/mcpand provide links tohelp.clueso.iofor setup documentation. These are legitimate resources owned by the skill's author and are used for the intended purpose of the skill.
Audit Metadata