Back to skill
Skillv1.0.0
ClawScan security
Grab Food · ClawHub's context-aware review of the artifact, metadata, and declared behavior.
Scanner verdict
BenignApr 27, 2026, 11:04 AM
- Verdict
- benign
- Confidence
- high
- Model
- gpt-5-mini
- Summary
- This is a purely informational, instruction-only skill about Grab's history and business model and it does not request permissions, install code, or perform actions outside its stated purpose.
- Guidance
- This skill is informational-only and does not require credentials or install anything, so it poses minimal security risk. Consider that the source/homepage are unspecified — verify important facts against trusted references before using the content for decisions or publication.
Review Dimensions
- Purpose & Capability
- okName, description and SKILL.md all describe a company/history/business-model summary; nothing requested (no env vars, binaries, or installs) is out of scope.
- Instruction Scope
- okSKILL.md contains static content and reading guidance only — it does not instruct the agent to run commands, access files, or exfiltrate data.
- Install Mechanism
- okNo install spec and no code files — nothing is written to disk or downloaded as part of this skill.
- Credentials
- okRequires no environment variables, credentials, or config paths; requested access is proportional (none) to the stated purpose.
- Persistence & Privilege
- okalways is false and the skill does not request elevated or persistent privileges or modify other skills/config; autonomous invocation defaults are unchanged.
