ClawHub
Back to skill

Security audit

Content Writer

Security checks across malware telemetry and agentic risk

Overview

This SEO content-writing skill is coherent and purpose-aligned, with limited disclosed memory use and gated external publishing-related actions.

Before installing, be aware that the skill may proceed with estimated SEO analysis when analytics data is missing and may choose a small set of competitor pages itself. Review any generated refresh plan before publishing, connecting analytics tools, or using live index-push credentials.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • 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)

Autonomous Decision Making

Medium
Category
Excessive Agency
Content
**Continue silently (never stop for):**
- Missing analytics/ranking history — score decay from on-page signals (dated claims, broken links, stale stats), label findings Estimated, and proceed.
- A "refresh" request with no existing URL — note the mismatch once and run `--mode new`.
- Which republish-date treatment to apply — follow the Step 8 thresholds without asking.
- Which competitor pages to deep-dive when several are named — pick the top-ranking 3 and proceed.

## Reference Materials
Confidence
90% confidence
Finding
without asking

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

Detected: suspicious.secret_argv_exposure

Instructions pass high-value credentials through process argv.

Critical
Code
suspicious.secret_argv_exposure
Location
SKILL.md:63