Rubicon Sentinel v2 — Sovereign Forge

Rubicon Sentinel v2 is the no-cope geopolitical sovereignty scanner for OpenClaw. Inspired by Secretary Marco Rubio's Munich 2026 masterclass, it delivers re...

This skill appears to do what it claims (web-search driven sovereignty scoring) but has a few mismatches you should resolve before installing or supplying secrets: 1) The runtime docs reference an optional TWITTER_BEARER_TOKEN and image-generation credentials but the registry declares no required env vars—do not provide tokens until the skill explicitly declares how it accepts/stores them. 2) The skill claims 'persistent memory' but gives no detail on where scan history is kept or for how long—ask how memory is managed and whether past scans or fetched results are retained or shared. 3) The content is explicitly partisan and uses loaded framing (quotes, 'red pills', 'forge' language); consider bias risk if you need neutral analysis. If you decide to proceed, test the skill in a limited environment without supplying credentials, and request the author update the metadata to declare optional env vars and storage behavior so you can make an informed decision.

Type: OpenClaw Skill Name: rubicon Version: 2.0.0 The skill is classified as suspicious due to its extensive reliance on `web_search` and `web_fetch` capabilities, as instructed in `SKILL.md` and guided by `references/queries.md`. While these tools are necessary for the skill's stated purpose of geopolitical analysis, they inherently introduce a significant attack surface for potential second-order prompt injection or data misinterpretation by the AI agent from untrusted external content. No direct evidence of malicious intent, data exfiltration beyond stated API usage, or explicit harmful instructions was found within the skill bundle.