proxy-token-optimizer

Optimize LLM token usage and API costs for the openclaw-manager proxy platform. Provides model-tier routing (route simple prompts to glm-4.7-flashx instead o...

This skill appears to do what it claims (routing, context optimization, heartbeat config, and DB-backed usage reports) but there are red flags you should address before enabling it widely: - always: true is set. That forces this skill into every agent run. Remove or justify always: true unless you need the skill globally; prefer explicit invocation. - The platform-side scripts import app.database and app.settings and will query PostgreSQL. That requires running inside the openclaw-manager environment with DB credentials present — but the skill does not declare these credentials or config paths. Treat DB access as sensitive: require explicit user consent before running those commands and restrict where the skill can run. - If you plan to use the usage_report/quota_advisor features, run them manually from the openclaw-manager project root in a controlled environment first. Inspect the queries and ensure they only read required tables/columns and that the DB user has least privilege. - Because the skill writes files (AGENTS.md.optimized and other patches), review generated output before applying it to production configs. - If you enable autonomous invocation, restrict the skill's triggers or remove always: true; otherwise the agent may call into code that touches your DB without explicit operator confirmation. Bottom line: the code is coherent with the stated purpose, but the combination of always: true + undeclared DB access is disproportionate and worth fixing before installation.

Type: OpenClaw Skill Name: proxy-token-optimizer Version: 1.0.1 The skill bundle provides legitimate LLM cost-optimization tools but includes high-risk capabilities, such as direct access to the platform's PostgreSQL database to query sensitive usage records in 'usage_report.py' and 'quota_advisor.py'. It also utilizes the 'always: true' metadata flag in 'SKILL.md', which allows the skill to intercept and modify the agent's behavior for every prompt. While the code appears well-written and lacks clear evidence of malicious intent or data exfiltration, the combination of broad database access and persistent prompt-level interception meets the threshold for a suspicious classification.