Token Guard

Prevents LLM API 429 errors by estimating tokens, tracking quotas, throttling requests, detecting duplicates, caching responses, and auto-fallback by model.

Summary of things to consider before installing: - The implementation and documentation disagree. SKILL.md promises caching, duplicate detection, record_usage/cache_response/record_429 helpers and richer behavior; the shipped script only provides TokenGuard.check_quota(...) and saves simple usage/request counters. If you rely on the advertised APIs they will fail. Ask the author for a matching release or updated code. - The script writes a state.json file (usage counters and timestamps) into the skill's base directory by default. This is normal for quota tracking but confirm the path is acceptable and writable in your environment if you care about where files are stored. - There are no network calls, no environment variables read, and no obvious exfiltration of prompts/responses in the code. That reduces risk, but the mismatch between docs and code is a functional risk: an agent expecting missing methods may error or behave unpredictably. - Recommended actions: (1) run the script in a sandboxed environment to verify behavior, (2) request a corrected SKILL.md or an updated script implementing the advertised features (or modify the agent to only call check_quota), and (3) inspect/monitor the created state.json while testing to ensure no sensitive data is written. If you need the advertised caching/duplicate-detection, do not deploy this version until those features are implemented.

Type: OpenClaw Skill Name: token-guard Version: 1.5.0 The OpenClaw skill 'token-guard' is designed to prevent LLM API rate limits by tracking token usage and throttling requests. The `SKILL.md` documentation clearly outlines its purpose and features without containing any prompt injection attempts. The `scripts/token_guard.py` implementation uses standard Python libraries, manages its state locally via an atomically written `state.json` file, and does not perform any network calls, execute arbitrary commands, or access sensitive user data. While the 'compaction' logic could be manipulated by an agent to bypass quota limits for specific prompts, this is a functional bypass of the quota system, not a security vulnerability leading to RCE or data exfiltration. The skill aligns with its stated purpose and lacks any indicators of malicious intent or significant security risks.