Plausible

Query Plausible Analytics API for traffic stats, referrers, conversions, and custom events.

This skill appears coherent and only needs your Plausible API key. Before installing: (1) Provide the key via the PLAUSIBLE_API_KEY environment variable (do not paste it into chat). (2) Confirm you trust Plausible (or your self-hosted instance) because queries and the API key are sent to that endpoint. (3) Review ~/plausible/ after first run to see what the skill saved (site list, preferences, cached results); the skill claims not to store API keys. (4) Prefer using a read-limited or revocable API key if Plausible supports it, and rotate the key if you stop using the skill. (5) Because this is an instruction-only skill, behavior is driven by the agent—ensure the agent runtime environment enforces the intended file and network access policies if you require stricter controls.

Type: OpenClaw Skill Name: plausible Version: 1.0.1 The skill bundle is classified as benign. All files consistently describe a skill designed to query the Plausible Analytics API. The `SKILL.md` clearly outlines external endpoints (plausible.io or self-hosted instances) and the specific, non-sensitive data sent (site ID, query parameters). It explicitly states that the API key is sourced from the `PLAUSIBLE_API_KEY` environment variable and not stored, and that the skill does not access files outside `~/plausible/`. There is no evidence of data exfiltration, malicious execution, persistence mechanisms, or prompt injection attempts designed to subvert the agent for harmful purposes. The instructions are transparent and align with the stated purpose.