Back to skill
Skillv0.1.0
ClawScan security
tldr · ClawHub's context-aware review of the artifact, metadata, and declared behavior.
Scanner verdict
BenignFeb 27, 2026, 4:48 PM
- Verdict
- Benign
- Confidence
- high
- Model
- gpt-5-mini
- Summary
- The skill is an instruction-only wrapper for the local tldr client and its requirements/instructions match that purpose; the main irregularity is inconsistent packaging metadata (owner/slug/version) which should be verified before trusting the skill source.
- Guidance
- This skill appears to do what it says: use your local tldr CLI. Before installing: (1) confirm the tldr binary exists and was installed from a trusted package manager, (2) be aware that running 'tldr --update' will fetch pages from the tldr-pages network source (expected), and (3) verify the skill's origin because the bundle's _meta.json owner/slug/version do not match the registry metadata — that mismatch may indicate packaging errors or a mislabeled source. If you cannot verify the source, prefer not to enable the skill.
Review Dimensions
- Purpose & Capability
- okName and description match the runtime instructions and declared requirement (the 'tldr' binary). The skill only needs the tldr CLI to function. However, _meta.json in the bundle shows a different ownerId/slug/version than the registry metadata, which is an inconsistency in packaging/origin that should be checked.
- Instruction Scope
- okSKILL.md only instructs the agent to prefer using the tldr CLI and shows benign commands (tldr <command>, tldr --update, tldr --list). It does not request reading local files or unrelated environment variables. Note: tldr --update will fetch remote pages (expected behavior for tldr) which implies network activity to the tldr-pages source.
- Install Mechanism
- okNo install spec (instruction-only), so nothing is written to disk by the skill itself. This is the lowest-risk model for a skill of this type.
- Credentials
- okThe skill declares no required environment variables or credentials — proportional for a wrapper around a local CLI tool.
- Persistence & Privilege
- okalways:false (not force-included). disable-model-invocation is false (default autonomous invocation allowed) which is normal. The skill does not request extra persistent privileges or modify other skills' configs.