Ai Humanizer Backup
Security checks across malware telemetry and agentic risk
Overview
This appears to be a purpose-aligned offline writing-analysis/editing skill, with no evidence of credential use, exfiltration, persistence, or hidden execution, but users should note its AI-origin-concealment purpose and verify provenance before running the optional CLI.
This looks safe to use as an offline text editor/analyzer if you trust the package source. Be careful about using it to hide AI involvement where disclosure is expected, and verify the repository/version before running npm install or the standalone CLI.
VirusTotal
VirusTotal findings are pending for this skill version.
Risk analysis
Artifact-based informational review of SKILL.md, metadata, install specs, static scan signals, and capability signals. ClawScan does not execute the skill or run runtime probes.
The skill may help edit drafts, but it can also make AI-generated content harder to identify as AI-assisted.
The skill is explicitly designed to remove visible signs of AI-generated writing. That is disclosed and purpose-aligned, but it could mislead readers or AI-use reviewers if used where authorship transparency is required.
Humanize AI-generated text by detecting and removing patterns typical of LLM output. Rewrites text to sound natural, specific, and human.
Use it only in contexts where rewriting AI-assisted text is allowed, and keep any required AI-use disclosures.
Running the standalone CLI executes local package code and can read files you explicitly pass to it.
The README documents optional local Node.js execution and package installation for the standalone CLI. This is expected for the stated purpose and is user-directed, not automatic.
npm install # Score some text echo "This serves as a testament to innovation." | node src/cli.js score
Only install or run the CLI from a source you trust, and provide only drafts/files you intend to analyze.
It may be unclear whether this package is the same artifact as the registry listing or a copied/backup version.
The packaged _meta.json identifies a different slug/version than the registry listing for ai-humanizer-backup version 1.0.0, which is a provenance/version consistency issue rather than evidence of malicious behavior.
"slug": "ai-humanizer", "version": "2.1.0"
Verify the intended repository, owner, and version before relying on or globally installing the CLI package.