ClawHub

Delete File

Security checks across malware telemetry and agentic risk

Overview

This skill clearly does one sensitive but disclosed job: delete a user-owned PDF API Hub file by URL using that service's API key.

Install only if you trust pdfapihub.com and want agents to delete files from that service. Treat the API key as sensitive, confirm the exact uploaded-file URL before each delete, and avoid allowing the skill to run automatically from ambiguous cleanup requests.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (3)

Missing User Warnings

Medium
Confidence
93% confidence
Finding
The example demonstrates a destructive delete operation against a cloud file URL without any warning, confirmation, or explanation of the irreversible effect. Even though the API notes that only the uploading API key can delete the file, presenting the call plainly in a reusable skill example increases the chance of accidental or automated deletion by users or downstream agents.

Vague Triggers

Medium
Confidence
93% confidence
Finding
The skill exposes a destructive capability but does not define any trigger scope, confirmation requirement, or activation constraints. In an agent setting, vague invocation criteria can cause the delete action to be selected too broadly or automatically from ambiguous user requests, increasing the chance of unintended file deletion.

Missing User Warnings

Medium
Confidence
96% confidence
Finding
This skill performs irreversible deletion but does not include an explicit warning, confirmation, or safety language around the destructive operation. Even if backend authorization limits deletion to files uploaded under the same API key, an agent using this skill could still delete the operator's own files unintentionally when handling ambiguous or maliciously crafted prompts.

VirusTotal

66/66 vendors flagged this skill as clean.

View on VirusTotal