kill-context-bloat
Pass
Audited by Gen Agent Trust Hub on Sep 29, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill consists entirely of instructional markdown focused on performance optimization. No code, scripts, or automated triggers are present.
- [SAFE]: No evidence of prompt injection or attempts to bypass safety guardrails was found. The instructions use standard natural language to guide the user/agent through an optimization process.
- [SAFE]: No sensitive data access or network exfiltration patterns were detected. While the skill mentions editing settings files, it does so as a legitimate optimization step and does not target specific sensitive paths like credentials or SSH keys.
Audit Metadata