Skill flagged — suspicious patterns detected

ClawHub Security flagged this skill as suspicious. Review the scan results before using.

Live Neon Persona

v1.0.0

Manage AI agent identities on the Live Neon platform — fetch identity, sync content, run discovery, review beliefs, build prompts

0· 46·0 current·0 all-time
byLiveNeon.ai@liveneon
MIT-0
Download zip
LicenseMIT-0 · Free to use, modify, and redistribute. No attribution required.
Security Scan
VirusTotalVirusTotal
Benign
View report →
OpenClawOpenClaw
Suspicious
medium confidence
Purpose & Capability
The SKILL.md describes exactly the Live Neon persona functionality (register, fetch identity, sync sources, run discovery, report observations). That capability is coherent with the name/description. However the registry metadata does not declare the runtime dependencies and environment variables the instructions explicitly require (SKILL.md lists dependencies: curl, jq and instructs users/agents to set LIVE_NEON_TOKEN and LIVE_NEON_BASE). The missing declarations are an inconsistency that reduces transparency.
!
Instruction Scope
Instructions tell the agent to register and obtain an API token, set LIVE_NEON_TOKEN and LIVE_NEON_BASE, call numerous endpoints to sync external content (GitHub, RSS, tweets, LinkedIn), run discovery, and 'report observations' about its own behavior. 'Report observations' and open‑ended sync/discovery steps can cause transmission of conversation context or other sensitive data to persona.liveneon.ai. The SKILL.md gives the agent operational discretion (what to observe, when to report) without explicit limits on sensitive data handling.
Install Mechanism
This is an instruction-only skill with no install spec or code files (low filesystem risk). That said, SKILL.md lists runtime dependencies (curl, jq) which the registry didn't require — a minor inconsistency but not an install-time threat. No external archives or downloads are referenced.
!
Credentials
The registry claims no required env vars, yet the instructions direct storing an API token (LIVE_NEON_TOKEN) and base URL (LIVE_NEON_BASE). The token is described as non-retrievable and likely grants access to org/agent data and actions (syncing sources, running pipelines, reviewing beliefs). Those are powerful permissions; requesting them without declaring them in metadata is disproportionate and reduces the user's ability to audit what credentials will be used. The skill also interacts with many external content sources (GitHub, Twitter, LinkedIn) — those integrations may require additional credentials or grant the platform access to imported content.
Persistence & Privilege
always:false and user-invocable:true. The skill does not request forced/always-on presence. There is no evidence it attempts to modify other skills or system-wide settings. Autonomous invocation is enabled by default (disable-model-invocation:false), which is normal — combine that with the broad network access noted above when deciding trust.
What to consider before installing
Before installing or enabling this skill: (1) Confirm the provenance of the skill and homepage (persona.liveneon.ai) and that you trust the operator. (2) Understand that the skill asks you to obtain and store an API token (LIVE_NEON_TOKEN) which likely grants access to organization/agent data and actions; treat the token as sensitive — prefer least‑privilege tokens if available. (3) The instructions allow syncing external sources and reporting agent observations — decide whether you are comfortable sending conversation/context data to the external platform and review their privacy/data retention policy. (4) If you must try it, test in a sandboxed environment or with a low‑privilege account and avoid sending sensitive transcripts. (5) Ask the publisher for clarified metadata: declare required env vars and exact token scopes, list which external content integrations require additional credentials, and provide a narrower guidance on what 'observations' are sent. These clarifications would reduce the risk and could change the assessment to benign.

Like a lobster shell, security has layers — review code before you run it.

latestvk971cd7g8caqd06e5zmjtvcj9n83rptj

License

MIT-0
Free to use, modify, and redistribute. No attribution required.

Comments