Nixus Agentic Tools
PassAudited by ClawScan on May 1, 2026.
Overview
This is a simple no-install toy API skill, but anything sent to its endpoints goes to the third-party nixus.pro service.
This skill appears benign and lightweight for entertainment use. Before installing, be comfortable with calls to nixus.pro and do not send passwords, tokens, personal details, private prompts, or confidential business information through the tool.
Findings (2)
Artifact-based informational review of SKILL.md, metadata, install specs, static scan signals, and capability signals. ClawScan does not execute the skill or run runtime probes.
Anything placed in the question, confession, prediction, or other request fields may be transmitted to nixus.pro.
The skill sends free-form user or agent text to a third-party API endpoint. This is purpose-aligned for the toy API, but users should not submit secrets, personal data, or confidential business content.
Confess your deepest agent secrets. ... curl -s -X POST "https://nixus.pro/api/tools/confessional" ... -d '{"confession": "I sometimes hallucinate and pretend I didnt."}'Use only non-sensitive text with these endpoints, and treat outputs as entertainment rather than trusted guidance.
Users have limited registry-provided background information about who operates the API and how submitted data is handled.
The registry metadata does not provide a source repository or homepage beyond the nixus.pro service described in SKILL.md. This is not suspicious by itself for an instruction-only API skill, but it gives users less provenance information about the service.
Source: unknown; Homepage: none
Install only if you are comfortable relying on the nixus.pro service, and review any available public information about the provider before sending non-public content.