ia-writing
Security checks across static analysis, malware telemetry, and agentic risk
Overview
This is an instruction-only writing and editing skill with no code or install steps, though users should note that it helps remove AI-sounding language and its credential capability flags appear inconsistent with the actual artifacts.
This skill appears safe as a writing-style helper from the provided artifacts: it has no code, no install commands, and no credential requirements in the files. Use it responsibly for editing, and do not use it to hide AI involvement where disclosure is expected.
Static analysis
No static analysis findings were reported for this release.
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.
Readers may assume edited text was fully human-written if the user applies this skill in settings with authorship or AI-use disclosure requirements.
The skill explicitly helps make text sound less AI-generated. That is disclosed and purpose-aligned, but it can be misused where AI assistance must be disclosed.
Prose editing, rewriting, and humanizing text for natural tone... remove AI language.
Use the skill for clarity and tone, but disclose AI assistance where required by school, workplace, publication, or platform rules.
A user could be confused about whether this writing skill needs account tokens or sensitive credentials.
The metadata signals mention credential needs, while the declared requirements and instruction-only files do not show any credential use.
Capability signals: requires-oauth-token; requires-sensitive-credentials ... Primary credential: none
Do not provide OAuth tokens or sensitive credentials to this skill unless the publisher later documents a clear, necessary credential flow.