youmind-web-clipper
Pass
Audited by Gen Agent Trust Hub on Mar 17, 2026
Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill utilizes the
youmindCLI for board management and content creation. It also uses standard shell commands to verify environment variables. - [COMMAND_EXECUTION]: The skill configuration allows the use of
node -e, which enables dynamic execution of JavaScript strings, though no malicious usage is observed in the provided workflow. - [EXTERNAL_DOWNLOADS]: The skill installs the
@youmind-ai/clipackage from the NPM registry. This package is an official resource belonging to the skill author (YouMind-OpenLab). - [PROMPT_INJECTION]: The skill is vulnerable to indirect prompt injection via the page summarization feature.
- Ingestion points: User-provided URLs are ingested into the workflow to be processed and summarized (SKILL.md).
- Boundary markers: No explicit delimiters or instructions to ignore embedded commands are present when handling external page content.
- Capability inventory: The skill has access to
Bash(includingyoumindCLI andnode) and file system check operations (SKILL.md). - Sanitization: No sanitization or filtering of the fetched web content is performed before potential summarization.
Audit Metadata