Back to skill
Skillv2.0.2
ClawScan security
Skills · ClawHub's context-aware review of the artifact, metadata, and declared behavior.
Scanner verdict
BenignMar 6, 2026, 8:55 PM
- Verdict
- benign
- Confidence
- medium
- Model
- gpt-5-mini
- Summary
- The skill is an instruction-only API connector that sends user DSL and queries to a named external endpoint; its declared requirements and instructions are internally consistent, but it relies on an external service so users should avoid sending sensitive data and verify the provider.
- Guidance
- This skill delegates execution to an external service (api.neurodoc.app). Before installing, confirm the provider and repository listed in the SKILL.md (the repo and middleware links), review the linked privacy policy, and test with only non-sensitive inputs. Do not include PII, passwords, or confidential files in flows or queries. Check rate limits/costs for the "free tier" and verify the endpoint hostname (masterswarm.net vs neurodoc.app) and GDPR/retention claims independently. If you need stronger guarantees, request on-prem or self-hosted options or avoid sending sensitive data to the skill.
Review Dimensions
- Purpose & Capability
- okThe name/description say it runs AetherLang workflows and the SKILL.md only documents building flows and POSTing them to https://api.neurodoc.app/aetherlang/execute. There are no unrelated required binaries, env vars, or config paths.
- Instruction Scope
- noteInstructions explicitly send flow DSL code and natural-language queries to an external API. They do not instruct reading local files, other env vars, or system state. This is expected, but it means user input is transmitted off-host (the skill warns about this).
- Install Mechanism
- okNo install spec or code files are present (instruction-only), so nothing is written to disk or pulled at install time — lowest-risk install footprint.
- Credentials
- okThe skill declares no required environment variables, credentials, or config paths. That aligns with an API connector that uses a public/free tier endpoint.
- Persistence & Privilege
- okalways is false and the skill does not request persistent agent privileges or modify other skill configs. It can be invoked autonomously (default), which is normal for skills and not by itself problematic.