spend-circuit-breaker
Pass
Audited by Gen Agent Trust Hub on Mar 21, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill operates as a purely local utility for budget management. It estimates costs based on model price tables and local token usage logs.\n- [DATA_EXFILTRATION]: The script reads files from the
~/.openclaw/sessions/directory. This access is necessary to calculate token consumption. Because there are no network-bound operations (e.g., requests, socket calls), there is no risk of data being sent to an external server.\n- [PROMPT_INJECTION]: While the skill processes session logs that contain untrusted conversation data, it only extracts numerical token usage metrics. It does not evaluate the content of the logs as instructions or code, effectively mitigating indirect prompt injection risks.\n - Ingestion points:
~/.openclaw/sessions/*.jsonlincheck.py\n - Boundary markers: None present\n
- Capability inventory: Modifies local
state.yamlfile to setcircuit_openflag; no direct command execution or network access\n - Sanitization: Data is parsed as structured JSON; numerical token fields are cast to integers before cost calculation.
Audit Metadata