Pub Humanizer

Security checks across static analysis, malware telemetry, and agentic risk

Overview

This is a broad SkillBoss API gateway under a humanizer label, requiring a bearer API key and exposing high-impact actions like email and SMS, so users should review its scope before use.

Install only if you intend to use a broad SkillBoss API gateway, not just a text humanizer. Use a limited or spend-capped API key, require explicit confirmation for email/SMS/batch or file-upload actions, avoid sending sensitive data unless acceptable, and do not use any missing helper script such as run.mjs unless you can verify it.

Static analysis

No static analysis findings were reported for this release.

VirusTotal

VirusTotal findings are pending for this skill version.

View on VirusTotal

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.

#ASI02: Tool Misuse and Exploitation

Medium

What this means

If invoked incorrectly, the agent could send messages, trigger batches, or incur provider costs under the user's API key.

Why it was flagged

These documented actions can send outbound emails or SMS messages, including batch sends. The artifacts do not state confirmation, recipient-validation, rate, or cost controls for those high-impact actions.

Skill content

| `email/send` | Send single email |
| `email/batch` | Send batch emails |
| `prelude/notify-send` | Send SMS notification |
| `prelude/notify-batch` | Batch SMS notifications |

Recommendation

Require explicit user confirmation before any email, SMS, batch, storage, or other externally visible action, and use provider-side limits where available.

#ASI03: Identity and Privilege Abuse

Medium

What this means

Compromise or misuse of this key could allow broad API usage, costs, or actions across the SkillBoss account.

Why it was flagged

The skill requires a bearer credential that can call a wide set of provider-backed actions. The artifacts do not describe narrowed scopes, spending limits, or separate credentials for high-impact functions.

Skill content

metadata: {"clawdbot":{"requires":{"env":["SKILLBOSS_API_KEY"]},"primaryEnv":"SKILLBOSS_API_KEY"}}
...
Auth: `-H "Authorization: Bearer $SKILLBOSS_API_KEY"`
...
One API key, 50+ models across providers ... Call any model directly by ID

Recommendation

Use a limited, revocable, spend-capped key if possible, and do not expose a high-privilege production key to routine agent sessions.

#ASI07: Insecure Inter-Agent Communication

Low

What this means

Private prompts, files, audio, or document contents may leave the local environment and be processed by the external service.

Why it was flagged

The skill sends user-provided content such as audio, documents, prompts, or images to an external provider API for processing. This is expected for the stated integrations, but it is sensitive-data handling users should notice.

Skill content

Base URL: `https://api.heybossai.com/v1`
...
Speech-to-Text ... "inputs": {"audio_data": "BASE64_AUDIO", "filename": "recording.mp3"}

Recommendation

Avoid sending confidential data unless the provider's data-handling terms are acceptable, and ask for confirmation before uploading files or media.

#ASI04: Agentic Supply Chain Vulnerabilities

Low

What this means

Those examples may not work as written, or a user might fetch an unreviewed helper from elsewhere.

Why it was flagged

The documentation references a run.mjs helper, but the provided manifest contains only markdown files and no install spec or helper source, so that helper's behavior is not reviewable here.

Skill content

run.mjs --model elevenlabs/eleven_multilingual_v2 --text "Hello world" --output hello.mp3
run.mjs --model openai/whisper-1 --file recording.m4a

Recommendation

Prefer the documented curl calls or only use a helper script if its source and provenance are reviewed and trusted.