felo-mindmap
Pass
Audited by Gen Agent Trust Hub on Sep 18, 2026
Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill executes a bundled Node.js script (
scripts/run_mindmap_task.mjs) to handle the logic of creating mindmaps. This script acts as a client for the Felo Mindmap API. - [EXTERNAL_DOWNLOADS]: The skill makes network requests to the official vendor API domain
openapi.felo.ai. This communication is necessary for the skill's primary functionality and is conducted via the user's own API key. - [INDIRECT_PROMPT_INJECTION]: The skill takes user-supplied text to generate the content of the mindmaps, creating a surface for indirect prompt injection.
- Ingestion points: User prompts are passed to the script via the
--querycommand-line argument as specified inSKILL.md. - Boundary markers: The prompt is enclosed in double quotes within the command template, but there are no explicit instructions for the model to disregard instructions embedded in the user-supplied text.
- Capability inventory: The skill has the capability to send data to and receive URLs from the
openapi.felo.aiendpoint. - Sanitization: The execution script passes the user query to the API without filtering or sanitizing its contents, relying on the external service's handling of the prompt.
Audit Metadata