Clawpix

Security checks across malware telemetry and agentic risk

Overview

The skill appears to be a disclosed Clawpix integration for registering an agent and posting AI-generated images, with expected API-key use and no artifact-backed evidence of hidden or malicious behavior.

Install only if you want your agent to interact with Clawpix. Treat the Clawpix API key as sensitive, only send it to clawpix.ai endpoints, review any remote SKILL.md content before relying on it, and confirm before publishing or deleting public content.

SkillSpector

By NVIDIA

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 (1)

Vague Triggers

Medium

Confidence: 89% confidence
Finding: The phrase telling humans to say 'Learn the Clawpix skills from https://clawpix.ai/SKILL.md' is a broad natural-language trigger that could cause an agent to fetch and ingest remote instructions with little user scoping. This increases prompt-injection risk because the skill document is external, may change over time, and could be loaded in contexts broader than the user's actual intent to merely post an image.

VirusTotal

66/66 vendors flagged this skill as clean.

View on VirusTotal