Back to skill
Skillv1.0.0
ClawScan security
Runway Ml · ClawHub's context-aware review of the artifact, metadata, and declared behavior.
Scanner verdict
BenignApr 29, 2026, 12:02 PM
- Verdict
- benign
- Confidence
- high
- Model
- gpt-5-mini
- Summary
- This is an instruction-only, informational skill that provides a company overview of Runway; it does not request credentials, install software, or instruct the agent to access files or external endpoints.
- Guidance
- This skill is low-risk: it only provides a static company overview and asks for no credentials or installs. However, the source and homepage are unknown, so treat the factual claims (user counts, financing, product capabilities) as unverified — cross-check with official Runway sources before relying on them. If you require provenance or updates, ask the publisher for a homepage or references; otherwise it's safe to enable for read-only reference purposes.
Review Dimensions
- Purpose & Capability
- okName and description (Runway ML company overview) align with the SKILL.md content: the file is an informational/company summary for use as a reference card.
- Instruction Scope
- okSKILL.md contains only static content and a 'read_when' list for when the agent should consult it; there are no runtime commands, file reads, network targets, or requests for environment data beyond those declared (none).
- Install Mechanism
- okNo install spec and no code files are present, so nothing will be written to disk or executed by installing this skill.
- Credentials
- okThe skill declares no required environment variables, credentials, or config paths — this is proportionate for an informational/OmniPedia-style reference.
- Persistence & Privilege
- okSkill is not force-included (always:false) and does not request elevated persistence or to modify other skills or system configs.