ClawHub
Back to skill

Security audit

terry-camsnap

Security checks for vulnerabilities and agentic risk

Overview

The skill’s webcam snapshot purpose is clear, but its invocation uses raw Bash arguments in a way that can allow command injection and depends on an unreviewed local script.

Review this before installing. Only use it if you trust the missing `camsnap.py` implementation and are comfortable granting webcam and local file-write access. Avoid passing untrusted filenames or options until the command is changed to structured, validated argument handling without raw shell interpolation.

A.I.G

Vulnerability Patterns
  • Insecure Skill Coding PracticesFinds exploitable flaws such as hardcoded secrets or command injection
  • Skill Instruction HijackingAlters the agent's session goals or safety constraints when the skill loads
  • Agent Memory PoisoningWrites attacker-controlled rules into memory that affect later sessions
  • Remote Payload Retrieval and ExecutionFetches external code whose behavior can change after review
  • Embedded Malicious CodeShips malicious scripts inside the skill and executes them locally
Findings (1)

T09 · Insecure Skill Coding Practices

Error
Location
SKILL.md:16
Finding

Command Injection Through Unquoted User-Controlled Arguments

Content
View full analysis
Remediation
View remediation

SkillSpector

Vulnerability Patterns
  • 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
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (1)

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The skill enables webcam access and writes captured image data to disk, but its description and usage text do not explicitly warn the user about those privacy-sensitive actions. In an agent setting, this can lead to users invoking the skill without fully informed consent, increasing the risk of unexpected image capture and local storage of sensitive data.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.