aiq-research
Pass
Audited by Gen Agent Trust Hub on Jul 15, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill and its associated scripts follow security best practices. No malicious code, obfuscation, or unauthorized access attempts were detected during the analysis.
- [COMMAND_EXECUTION]: The skill executes a local Python helper script (
scripts/aiq.py) to interact with the research backend. This script features comprehensive validation, including UUID checks for job identifiers and hostname/protocol verification for the server URL. It avoids the use of dangerous functions likeeval()oros.system()and does not invoke subprocesses. - [DATA_EXFILTRATION]: The skill transmits user-provided research queries to a configured AI-Q server. This is the intended and documented behavior. The implementation mitigates exfiltration risks by requiring HTTPS for remote endpoints, validating the URL format to prevent credential leakage, and instructing the agent to explicitly confirm the target backend with the user before transmission.
- [REMOTE_CODE_EXECUTION]: No remote code execution patterns were found. The skill relies entirely on local scripts and does not install or download external packages or executables at runtime.
Audit Metadata