mindmap
Pass
Audited by Gen Agent Trust Hub on Sep 2, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill fetches the
markmapJavaScript library from external Content Delivery Networks (CDNs) to enable interactive features in the generated HTML. It also utilizesplaywrightto download and managechromiumbrowser binaries required for PNG image generation. - [COMMAND_EXECUTION]: The instructions require the agent to run a local Python script (
skills/shared/scripts/mindmap.py) via the shell to convert Markdown files into HTML and image outputs. - [INDIRECT_PROMPT_INJECTION]: The skill processes user-supplied Markdown content, creating an attack surface for instructions embedded in the data. 1. Ingestion points: Untrusted data enters the context via the Markdown outline input (SKILL.md). 2. Boundary markers: Absent; the skill does not explicitly instruct the agent to ignore instructions embedded in the user content. 3. Capability inventory: The skill performs file writes to
outputs/and network operations to fetch CDN resources via themindmap.pyscript. 4. Sanitization: Absent; the instructions do not indicate that the script filters or sanitizes inputs before they are rendered in the browser.
Audit Metadata