Back to skill
Skillv1.0.0
ClawScan security
Basf Se · ClawHub's context-aware review of the artifact, metadata, and declared behavior.
Scanner verdict
BenignApr 29, 2026, 7:03 PM
- Verdict
- benign
- Confidence
- high
- Model
- gpt-5-mini
- Summary
- This is a self-contained, instruction-only skill that provides an informational writeup about BASF; its content and lack of requested permissions are consistent with that purpose.
- Guidance
- This skill appears to be a plain informational article about BASF and does not request credentials or install code, so it is internally coherent and low-risk. Before relying on it for important decisions, verify facts against an official source (company website, filings) because the registry lists no homepage or publisher information. If you expected the skill to perform actions (API calls, data lookups, or automation), note that it contains only static content and will not do those things.
Review Dimensions
- Purpose & Capability
- noteThe name and description promise an informational profile of BASF; the SKILL.md is exactly that (history, business structure, data). There are no unexpected requirements. One minor note: the skill's source/homepage is unknown in the registry metadata, so provenance is unclear, but this does not affect its functional coherence.
- Instruction Scope
- okSKILL.md contains static, topical instructions and content (what to read/cover) and does not instruct the agent to read system files, environment variables, or transmit data to external endpoints. No scope creep detected.
- Install Mechanism
- okThere is no install spec and no code files; this is instruction-only and therefore writes nothing to disk and installs nothing. This is the lowest-risk install profile.
- Credentials
- okThe skill requests no environment variables, credentials, or config paths. There is no disproportionate access requested relative to the described purpose.
- Persistence & Privilege
- okalways is false and the skill does not request elevated/persistent privileges or modifications to agent/system configuration. Model invocation is enabled (the platform default) which is appropriate for this kind of skill.