twitter-command-center-search-post
Pass
Audited by Gen Agent Trust Hub on Sep 17, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONDATA_EXFILTRATION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill makes network requests to the vendor's API endpoint at
api.aisa.oneto retrieve public Twitter data and perform account-related actions. - [COMMAND_EXECUTION]: Provides and utilizes two Python scripts (
scripts/twitter_client.pyandscripts/twitter_oauth_client.py) to facilitate interaction with the AIsa service. It also includescurlcommand examples for direct API access. - [DATA_EXFILTRATION]: For its primary functionality, the skill reads local media files (images and videos) from the agent's workspace and transmits them to the AIsa relay service for uploading to Twitter/X.
- [SAFE]: No malicious patterns such as prompt injection, obfuscation, or unauthorized privilege escalation were detected. The skill explicitly instructs agents to avoid requesting user passwords and relies on secure environment variable management for API credentials.
Audit Metadata