context-manager
Pass
Audited by Gen Agent Trust Hub on May 5, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill is entirely instructional and does not contain any executable scripts (.sh, .py, .js) or command-line operations. The core logic is defined in markdown instructions for the AI's persona.
- [SAFE]: No network communication or data exfiltration patterns were found. The skill does not use tools like curl or wget, and the frontmatter explicitly limits tool access.
- [SAFE]: The JSON assets (
context_system_query.json,progress_tracking.json) contain only static configuration and status data with no signs of obfuscation or malicious payloads. - [SAFE]: There are no attempts at prompt injection or bypassing safety filters. The instructions focus on best practices for data management, including security-centric topics like encryption and access control.
Audit Metadata