Glin Profanity
PassAudited by VirusTotal on May 12, 2026.
Overview
Type: OpenClaw Skill Name: glin-profanity Version: 1.0.0 The skill bundle consists of metadata and a `SKILL.md` file describing a profanity detection library. The `SKILL.md` content provides standard installation instructions (`npm install`, `pip install`) and usage examples for the library. There is no evidence of prompt injection against the AI agent, data exfiltration, malicious execution, persistence mechanisms, or obfuscation within the provided files. All content appears to be aligned with the stated purpose of a content moderation library.
Findings (0)
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.
Installing the wrong or compromised package could run untrusted third-party code in the user's development environment.
The skill directs users to install external packages without version pinning. This is purpose-aligned for a library skill, but users should verify the package identity and provenance.
npm install glin-profanity # Python pip install glin-profanity
Verify the npm/PyPI package and GitHub project, pin known-good versions, and use standard dependency scanning before adding it to an application.
If copied directly into a live chat or comment system, legitimate messages could be removed and users could be warned automatically.
The example shows automated moderation actions based on detector output. This fits the stated purpose, but deletion and user warnings can have real impact if false positives occur.
if (filter.isProfane(msg.text)) {
deleteMessage(msg);
warnUser(msg.author);
}Use clear moderation policies, logging, thresholds, and human review or appeal paths for high-impact moderation actions.