context-not-control
Pass
Audited by Gen Agent Trust Hub on Apr 17, 2026
Risk Level: SAFENO_CODE
Full Analysis
- [SAFE]: The skill consists entirely of instructional markdown and test case JSON data. It focuses on explaining the 'Context not Control' management philosophy.
- [NO_CODE]: There are no executable scripts, shell commands, or binary files associated with this skill. It does not introduce any programmatic vulnerabilities.
- [EXTERNAL_DOWNLOADS]: No external resources, dependencies, or remote scripts are requested or downloaded.
- [DATA_EXFILTRATION]: No mechanisms for accessing the file system, environment variables, or network are present.
- [PROMPT_INJECTION]: The instructions do not attempt to bypass safety filters or override the agent's core system prompts. It uses standard triggers to define when the management advice should be applied.
Audit Metadata