context-budget-guard
Pass
Audited by Gen Agent Trust Hub on Oct 9, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: No security issues were detected. The skill performs local context usage estimation based on session time and stores its state in a dedicated local directory.
- [DATA_EXFILTRATION]: The skill does not access sensitive system files or credentials. All file operations are restricted to its own state file in the user's home directory (~/.openclaw/skill-state/...). No network connectivity is requested or used.
- [DYNAMIC_EXECUTION]: The Python script uses yaml.safe_load() for parsing its state file, which prevents arbitrary code execution vulnerabilities during deserialization.
- [PROMPT_INJECTION]: The instructions in SKILL.md are purely functional and do not attempt to bypass safety filters or override agent instructions.
Audit Metadata