ClawHub
Back to skill

Security audit

Converter

Security checks for vulnerabilities and agentic risk

Overview

This skill is a straightforward local file-conversion helper with no evidence of hidden upload, persistence, or privilege-seeking behavior.

Install only if you are comfortable letting the agent propose and run local conversion commands over files you choose. For batch commands, confirm the matched files and run them in the intended folder or on copies when the source files matter.

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
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • 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)

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
96% confidence
Finding

The example uses magick mogrify -format webp *.jpg, and mogrify performs in-place/bulk modifications on matched files rather than creating a clearly isolated output set. In a conversion skill, presenting this as a ready-to-execute next step without warning can cause unintended destructive changes, mass overwrite behavior, or difficult-to-reverse user data loss if run in the wrong directory or with broader globs than intended.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The trigger list contains generic phrases like 'convert file', 'change format', and 'convert images' that can match a wide range of ordinary user requests beyond a narrowly scoped skill invocation. Overly broad activation can cause the skill to engage unexpectedly, increasing the chance it influences unrelated workflows or gains access to file-handling tasks when the user did not intend to invoke this specific converter.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.