ClawHub
Back to skill

Security audit

Update Docs on Code Change

Security checks across malware telemetry and agentic risk

Overview

This is a prose-only documentation helper skill whose requested behavior matches its stated purpose and does not add hidden execution, credentials, persistence, or unrelated access.

Install this if you want an agent to notice when code changes should be reflected in docs. Review generated documentation diffs as usual, especially changelog, migration guide, and API examples, because the trigger wording is intentionally broad and may produce extra documentation edits.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (1)

Vague Triggers

Medium
Confidence
90% confidence
Finding
The skill metadata and description repeatedly use broad automatic-trigger language such as 'Automatically update' and 'Triggers on code modifications,' without clear scoping constraints, approval requirements, or repository/path boundaries. In an agentic environment, this can cause the skill to activate on many ordinary code changes and perform documentation edits unexpectedly, increasing the risk of unintended file modifications, noisy commits, or incorrect documentation churn.

VirusTotal

63/63 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.