refresh-article-screenshots
Pass
Audited by Gen Agent Trust Hub on Sep 26, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTIONEXTERNAL_DOWNLOADS
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes help articles, which are untrusted external data sources, creating a vulnerability surface for indirect prompt injection. 1. Ingestion points: Help article projects and content (SKILL.md). 2. Boundary markers: Absent. 3. Capability inventory: Modifies images within articles using the clueso-mcp toolset. 4. Sanitization: Absent.
- [COMMAND_EXECUTION]: The skill documents the command
claude mcp add --transport http Clueso https://connect.clueso.io/mcpto configure the environment with the required MCP connector. - [EXTERNAL_DOWNLOADS]: The skill fetches connector configuration from the official vendor domain
connect.clueso.io.
Audit Metadata