ClawHub
Back to skill

Security audit

gent-skill

Security checks for vulnerabilities and agentic risk

Overview

The skill is rated benign with medium confidence: scanners found no AIG issues, while noting that prompts go to an external image provider without a privacy warning; inspection was partial because some referenced paths were missing.

The verdict is benign, but confidence is medium and the scan was partial: although all seven listed components were scanned, some referenced paths were missing. Before installing, consider whether you are comfortable sending prompts to gen1.diversityfaces.org, especially if they contain sensitive information.

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
  • Output HandlingUnvalidated Output Injection, Cross-Context Output, Unbounded Output
  • 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 (2)

The workflow sends user prompts to an external image-generation provider without a privacy warning.

Medium
Category
Output Handling
Confidence
92% confidence
Finding

The skill's workflow routes user prompts through gen1.diversityfaces.org, rather than merely listing an available tool. Although it names the provider, it does not warn that prompt content leaves the user's environment or advise against submitting sensitive information; the Safety & Limits section only addresses key protection, quotas, and failures.

Content

No source excerpt is available for this finding.

Skill Enumeration

Medium
Category
Agent Snooping
Confidence
85% confidence
Finding

Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.

Content

Scanner excerpt · SKILL.md (reported line 74)May include surrounding context.

md
- Image generation: `https://gen1.diversityfaces.org/api/generate/custom`
- Video orchestration: use `skills/ai-video-gen/generate_video.py`, `images_to_video.py`, `add_voiceover.py` (subdirectory scripts)
- FFmpeg patterns: documented in ffmpeg-video-editor usage (trim, merge, resize, effects) — describe, do not enumerate other SKILL.md files
- Figma design: use figma skill for layout overlays, typography, brand marks

## Output policy