Back to skill
Skillv1.0.0
ClawScan security
Humanizer · ClawHub's context-aware review of the artifact, metadata, and declared behavior.
Scanner verdict
BenignFeb 26, 2026, 10:42 PM
- Verdict
- benign
- Confidence
- high
- Model
- gpt-5-mini
- Summary
- The skill's claims, instructions, and footprint are internally consistent with an editing/humanizing tool; it doesn't request credentials or install anything, but it will rewrite content (including adding opinions/first‑person voice) so outputs should be reviewed before publication.
- Guidance
- This skill appears coherent and low-risk from an installation/credential standpoint, but its instructions intentionally allow subjective rewriting (adding opinions, using first person, changing rhythm) and could modify factual wording or introduce new assertions. Before installing or granting file-editing permissions: (1) test it on non-sensitive sample texts, (2) review all outputs carefully for factual accuracy and unintended changes, (3) avoid running it over confidential or authoritative documents without human review, and (4) if you plan to let the agent use Read/Write/Edit tools, restrict those permissions to specific files or folders you trust.
Review Dimensions
- Purpose & Capability
- okName, description, and SKILL.md all describe the same editing/humanizing functionality. There are no unrelated required binaries, env vars, or installs declared, so the requested surface is proportional to the stated purpose.
- Instruction Scope
- noteThe runtime instructions direct the agent to detect 24 AI patterns and rewrite text to 'add soul' (inject opinions, first‑person voice, varied rhythm). That is coherent with a humanizer but is inherently subjective and can alter factual phrasing or introduce new subjective content; SKILL.md also lists allowed-tools (Read/Write/Edit/Grep/Glob) which would permit file I/O if the agent is granted those tool permissions—SKILL.md itself does not name specific file paths.
- Install Mechanism
- okInstruction-only skill with no install spec and no code files; lowest-risk installation surface (nothing is written to disk by the skill package itself).
- Credentials
- okNo environment variables, credentials, or config paths are requested; requested access is proportional to an editing tool.
- Persistence & Privilege
- okalways is false and the skill does not request persistent or cross-skill privileges. Autonomous invocation is allowed (platform default) but not combined with other concerning flags.