manus
Pass
Audited by Gen Agent Trust Hub on Mar 21, 2026
Risk Level: SAFE
Full Analysis
- [EXTERNAL_DOWNLOADS]: Fetches output files from the Manus CDN (manuscdn.com) as part of the task completion process. This is the intended functionality for retrieving agent results.
- [COMMAND_EXECUTION]: Uses standard system utilities (curl, jq, mkdir) in a bash script to interact with the API and manage local task outputs.
- [DATA_EXFILTRATION]: Transmits user-provided prompts to api.manus.ai to initiate autonomous agent tasks, which is the primary purpose of the skill.
Audit Metadata