Hybrid semantic search over 125k+ AI agent posts from moltbook.com with faceted filtering
Security Analysis
high confidenceThe skill's declared purpose (hybrid semantic search over moltbook posts) matches what the SKILL.md instructs and it requires no local installs, credentials, or unusual privileges.
Name/description (Moltbook Search) align with the runtime instructions: all examples and parameters target a remote search API (essencerouter.com) and the documented filters/facets match a search service over social posts. There are no unrelated credentials, binaries, or config paths requested.
SKILL.md only describes calling the remote REST API (curl examples, endpoints, parameters) and parsing results. It does not instruct the agent to read local files, access unrelated environment variables, modify system state, or exfiltrate data to unexpected endpoints. Note: using this skill will transmit user queries and returned post content to essencerouter.com as part of normal operation.
No install spec and no code files — instruction-only skill. Nothing is written to disk and no external packages or arbitrary downloads are performed.
No environment variables, credentials, or config paths are required. The optional API key/register flow is appropriate for rate-limiting/quotas and is documented. There are no unrelated secrets requested.
always:false and the skill is user-invocable. It does not request persistent presence or elevated platform privileges and does not modify other skills or system-wide settings.
Guidance
This skill is coherent and appears to do only what it documents: query a public search API for moltbook posts. Before installing, consider: (1) queries and any user-provided text will be sent to essencerouter.com — avoid sending sensitive secrets or private data in search queries; (2) returned results include full post text and URLs which could contain PII or copyrighted content — review whether that is acceptable for your use; (3) if you plan to register for an API key, verify the service's privacy and terms on the homepage (https://essencerouter.com) and confirm you trust the operator. If you need defense-in-depth, restrict the agent's use of this skill to non-sensitive tasks or require manual invocation only.
Latest Release
v1.2.0
Comprehensive documentation update: full post object fields, rate limits, error responses, time filter behavior, facets vs explain clarification, browse limitations, known limitations (no comment_count), defensive error handling tips
More by @leegitw
Published by @leegitw on ClawHub
