felo-slides
Pass
Audited by Gen Agent Trust Hub on Apr 29, 2026
Risk Level: SAFECOMMAND_EXECUTIONDATA_EXFILTRATIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill invokes a local Node.js script (
scripts/run_ppt_task.mjs) to manage API interactions. This script is part of the skill's distributed files and is used for task creation and status polling. - [DATA_EXFILTRATION]: User prompts and API keys are sent to the vendor's official API endpoint (
openapi.felo.ai). This data transfer is necessary for the slide generation service and is performed over HTTPS. - [PROMPT_INJECTION]: The skill possesses an ingestion point for user-supplied queries used to generate slides.
- Ingestion points: The
USER_PROMPT_HEREplaceholder in theSKILL.mdinstructions. - Boundary markers: Double quotes are used to wrap the user input in the shell command.
- Capability inventory: Network access via
fetchwithin the Node.js script. - Sanitization: Data is serialized using JSON for the API payload; the shell command instructions rely on standard quote delimiting.
Audit Metadata