ClawHub
Back to skill

Security audit

Wjs Syncing Multicam

Security checks across malware telemetry and agentic risk

Overview

This skill appears to process user-selected media locally and write sync JSON sidecars, with one outdated documentation contradiction but no evidence of hidden re-encoding or unsafe behavior.

Install only if you are comfortable letting the skill process the media files you point it at and create or update .sync.json files next to them. The publisher should fix the stale _synced.MOV note to avoid confusion, and users should verify local ffmpeg/ffprobe and Python dependencies come from trusted sources.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (3)

Lp3

Medium
Category
MCP Least Privilege
Confidence
88% confidence
Finding
The skill documentation describes capabilities that imply reading local media files, writing sidecar JSON files, and invoking ffmpeg/jq or related scripts, yet no explicit permissions are declared. This creates a trust and containment gap: an agent or reviewer may assume the skill is documentation-only or low-privilege while it actually requires filesystem and shell access, increasing the risk of unintended file access or command execution in a sensitive environment.

Description-Behavior Mismatch

High
Confidence
93% confidence
Finding
The skill repeatedly promises sidecar-only behavior, but the implementation note admits the current script still emits re-encoded `_synced.MOV` files. This mismatch is security-relevant because users and orchestrators may grant the skill access expecting metadata-only writes, while it actually performs heavyweight media generation that can consume large disk space, overwrite naming-adjacent outputs, and create unauthorized derived copies of sensitive recordings.

Intent-Code Divergence

High
Confidence
95% confidence
Finding
The documentation makes strong no-modification and no-reencode guarantees, then later contradicts those guarantees by acknowledging that `_synced.MOV` files are still produced. Security-wise, this is dangerous because downstream systems may classify the skill as non-destructive and safe for restricted workflows, when in reality it performs additional file creation and media processing with storage, privacy, and operational consequences.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.