ClawHub
Back to skill

Security audit

Auto Shorts Repurposer

Security checks for vulnerabilities and agentic risk

Overview

This skill is a draft-only media repurposing helper with clear limits against posting, credential use, or hidden execution.

Before installing, make sure you have rights to reuse any source media and avoid sending private or sensitive recordings to third-party transcription services unless you trust that provider. The skill itself is scoped to draft planning and should not be used for automatic posting or account access.

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
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (1)

Credential Access

High
Category
Privilege Escalation
Confidence
70% confidence
Finding

Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.

Content

Scanner excerpt · SKILL.md (reported line 49)May include surrounding context.

md
- Deliver outputs as drafts only; do not publish or upload.

## Security notes
- Do not request account credentials or access tokens for posting.
- Avoid sharing source media beyond the user-provided context.

## Safe mode

Static analysis

No suspicious patterns detected.