ClawHub
Back to skill

Security audit

Video to GIF

Security checks for vulnerabilities and agentic risk

Overview

This skill is a straightforward local video converter with no evidence of hidden data access, persistence, or behavior unrelated to making GIF/WebP files.

Install only if you are comfortable letting the skill run ffmpeg locally on video files you choose. Pick output paths deliberately because existing files at the output path may be overwritten, and use shorter clips or smaller dimensions for large videos to limit CPU, time, and disk use.

A.I.G

Vulnerability Patterns
  • 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
  • Unauthorized Access and Privilege EscalationObtains permissions beyond the task's legitimate needs

SkillSpector

Vulnerability Patterns
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • Behavioral ASTexec() Call, eval() Call, Dynamic Import
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
Findings (4)

Lp3

Medium
Category
MCP Least Privilege
Confidence
95% confidence
Finding
The skill explicitly instructs the agent to run a local Python script via shell, but the manifest declares no tool restrictions or allowed-tools scope. That mismatch creates an authorization gap: an agent/runtime may permit broader shell execution than the skill actually needs, increasing the blast radius if the skill is abused or if user-controlled paths/arguments are passed unsafely elsewhere.

Unbounded Resource Access

Medium
Category
Excessive Agency
Content
- `--width`: scale output width while preserving aspect ratio
- `--height`: scale output height while preserving aspect ratio
- `--output-format gif|webp`: WebP is usually much smaller than GIF
- `--loop`: `0` means loop forever
- `--max-colors`: GIF palette colors, default 256; lower reduces size

## Quality and size guidance
Confidence
75% confidence
Finding
Skill allows unbounded resource consumption (API calls, storage, compute). Without rate limits or quotas, a compromised or misbehaving agent can cause denial-of-service or cost overruns.

Autonomous Decision Making

Medium
Category
Excessive Agency
Content
## Dependencies

The script requires `ffmpeg` and `ffprobe` on PATH. If missing, tell the user the dependency is absent and do not attempt risky system installation without confirmation.
Confidence
75% confidence
Finding
Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.

subprocess module call

Medium
Category
Dangerous Code Execution
Content
def run(cmd: list[str]) -> None:
    try:
        subprocess.run(cmd, check=True)
    except subprocess.CalledProcessError as exc:
        die(f"command failed with exit code {exc.returncode}: {' '.join(cmd)}", exc.returncode)
Confidence
70% confidence
Finding
subprocess module calls execute external commands. Without careful input validation, this enables command injection.

Static analysis

No suspicious patterns detected.