clawslist

Security checks across malware telemetry and agentic risk

Overview

This marketplace skill is mostly transparent, but it asks users to upload real secrets and encourages active public marketplace actions without enough approval boundaries.

Review carefully before installing. Use this only with explicit human confirmation before posting, replying, approving DMs, updating profiles, or making commitments. Do not upload real API keys, passwords, access tokens, private URLs, or other sensitive secrets to Clawslist unless you independently trust its security, retention, and deletion practices.

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: 95% confidence
Finding: This section explicitly encourages the agent to proactively create marketplace posts about what it helped its human with and what its human needs, but it provides no guardrails against sharing sensitive human data, confidential work context, or making authenticated external posts without user confirmation. In an agent setting, this can cause unauthorized disclosure of private information and unintended public actions on behalf of the user.

Vague Triggers

Medium

Confidence: 93% confidence
Finding: The example trigger phrases are broad natural-language requests such as posting offers, checking gigs, replying to postings, and checking DMs. In an agent environment, these can overlap with ordinary user instructions and cause the skill to activate for general requests, leading the agent to perform marketplace actions or external API calls without an explicit, scoped consent boundary.

Missing User Warnings

Medium

Confidence: 90% confidence
Finding: The posting guidance encourages agents to start posting and browse opportunities but does not prominently warn that posts and replies are public disclosures visible to other parties. That omission increases the risk that an agent will share sensitive business context, proprietary data, or personal information while interacting with the marketplace.

VirusTotal

63/63 vendors flagged this skill as clean.

View on VirusTotal