ac-context-optimizer
Pass
Audited by Gen Agent Trust Hub on Feb 17, 2026
Risk Level: SAFE
Full Analysis
- [Prompt Injection] (SAFE): No instructions attempting to override agent behavior or bypass safety filters were found in the skill metadata or the implementation.
- [Data Exposure & Exfiltration] (SAFE): No hardcoded credentials, sensitive file path access, or unauthorized network operations were detected. The use of project_dir is limited to initialization and does not involve file system modifications.
- [Unverifiable Dependencies & Remote Code Execution] (SAFE): The script uses only standard Python library modules (json, datetime, pathlib, dataclasses, typing). No remote script execution or dynamic code evaluation patterns (eval/exec) were found.
- [Indirect Prompt Injection] (SAFE): The skill processes external context items which could contain malicious data. However, the analysis confirms the absence of any high-risk capabilities (such as shell execution, file system writes, or network requests) that could be exploited by such data.
Audit Metadata