youmind-web-clipper
Pass
Audited by Gen Agent Trust Hub on Sep 22, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill requires the installation of the
@youmind-ai/clipackage from the official NPM registry. This tool is provided by the vendor to enable interaction with the YouMind API. - [INDIRECT_PROMPT_INJECTION]: The skill accepts external URLs as input, creating a potential surface for indirect instructions if the agent is asked to process or summarize the linked content.
- Ingestion points: The workflow in
SKILL.mdtakes a user-provided URL as its primary input. - Boundary markers: No specific delimiters or "ignore instructions" warnings are utilized when processing the URL content.
- Capability inventory: The skill utilizes shell execution for the
youmindCLI and has permission fornodeexecution as defined in its environment configuration. - Sanitization: There is no evidence of content sanitization for the data retrieved from the provided URLs before it enters the agent's context.
Audit Metadata