Back to skill
Skillv1.1.0
ClawScan security
skill-condenser · ClawHub's context-aware review of the artifact, metadata, and declared behavior.
Scanner verdict
BenignMay 1, 2026, 5:24 AM
- Verdict
- Benign
- Confidence
- high
- Model
- gpt-5.5
- Summary
- This instruction-only skill is coherently focused on condensing SKILL.md files and shows no evidence of hidden code, credentials, installation steps, or unsafe behavior.
- Guidance
- This appears safe to install as an instruction-only formatting/refactoring helper. As with any skill that rewrites SKILL.md content, review the condensed output before replacing an original skill file to ensure important safety instructions or operational details were not accidentally removed.
Review Dimensions
- Purpose & Capability
- okThe stated purpose and SKILL.md instructions align: compress verbose SKILL.md files while preserving structure and key content.
- Instruction Scope
- okInstructions are limited to reading a target SKILL.md, performing 2-3 condensation passes, and producing a condensed result with preservation constraints.
- Install Mechanism
- okNo install spec, binaries, code files, package dependencies, or runtime setup are present.
- Credentials
- okNo environment variables, credentials, network access, OS restrictions, or local system permissions are requested.
- Persistence & Privilege
- okArtifacts do not show background execution, persistence, privilege escalation, credential use, or autonomous account/system mutation.