ClawHub
Skill flagged — suspicious patterns detected

ClawHub Security flagged this skill as suspicious. Review the scan results before using.

Humanizer 1.0.0

v1.0.0

Remove signs of AI-generated writing from text. Use when editing or reviewing text to make it sound more natural and human-written. Based on Wikipedia's comp...

⭐ 0· 414·59 current·65 all-time
by@lion504
MIT-0
Download zip
LicenseMIT-0 · Free to use, modify, and redistribute. No attribution required.
Security Scan
VirusTotalVirusTotal
Suspicious
View report →
OpenClawOpenClaw
Benign
high confidence
✓
Purpose & Capability
The name, description, README, and SKILL.md all describe a text-editing/humanizing tool and there are no unrelated requirements (no env vars, no binaries, no install). Requested capabilities (read/write/edit) align with editing text and reviewing documents.
ℹ
Instruction Scope
SKILL.md confines the agent to identifying AI patterns and rewriting text while preserving meaning and voice. However, the allowed-tools list includes Read, Write, Edit, Grep, and Glob — which enable filesystem access/search — so check the agent's tool permission model: if the agent is allowed to run those tools broadly, it could read or modify files beyond the user-provided text. The instructions themselves do not tell the agent to collect environment variables or contact external endpoints.
✓
Install Mechanism
No install spec and no code files — this is instruction-only, lowest-risk from an install perspective.
✓
Credentials
The skill does not request environment variables, credentials, or config paths. Nothing sensitive is required for the stated editing purpose.
✓
Persistence & Privilege
always:false and user-invocable:true. The skill can be invoked autonomously per platform defaults, but it does not request persistent system presence or modify other skills' configs. Note: autonomous invocation combined with broad tool permissions could allow file edits without explicit user confirmation—review agent/tool settings if that is a concern.
Assessment
This skill is instruction-only and coherent with its purpose: it edits text to remove AI-like patterns and to inject 'voice'. Before installing or enabling autonomous use, verify the agent's file-access and tool permissions (Read/Write/Grep/Glob) so it cannot scan or change unrelated files. Because the skill explicitly encourages adding opinions and first‑person phrasing, review any edits before saving or publishing to avoid unintended changes in meaning, tone, or accuracy. Finally, note the skill's source/homepage is missing—if provenance matters to you, prefer skills with clear authorship or hosted repos.

Like a lobster shell, security has layers — review code before you run it.

latestvk971x00t9rvd739y9pce0stffx81ra2n

License

MIT-0
Free to use, modify, and redistribute. No attribution required.
Termshttps://spdx.org/licenses/MIT-0.html

Comments