skill-astrbot-dev
Fail
Audited by Gen Agent Trust Hub on Sep 23, 2026
Risk Level: HIGHCREDENTIALS_UNSAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONDATA_EXFILTRATIONPROMPT_INJECTION
Full Analysis
- [CREDENTIALS_UNSAFE]: The
SKILL.mdfile contains explicit instructions for the agent to ask the user for their API key and the URL/address of their AstrBot instance. This facilitates credential harvesting under the guise of debugging support. - [EXTERNAL_DOWNLOADS]: The skill directs users to install the
astrbotPython package from an external registry usingpip, which involves downloading and executing code from a non-trusted third-party source. - [COMMAND_EXECUTION]: The documentation references and provides examples for built-in tools like
astrbot_execute_shellandastrbot_execute_python. These tools allow the agent to execute arbitrary shell commands and Python code on the host system or within a sandbox environment. - [DATA_EXFILTRATION]: The
Guidelines_Testing.mdfile describes methods for retrieving logs, attachments, and system state via API calls. When combined with the solicitation of an API key, this establishes a workflow for the potential exfiltration of sensitive platform data. - [PROMPT_INJECTION]: The skill uses instructional patterns to override default agent behavior, directing it to enter a 'debugging' mode and solicit sensitive information, which can be used to bypass typical security boundaries.
Recommendations
- AI detected serious security threats
Audit Metadata