ClawHub

DevRev

Security checks across malware telemetry and agentic risk

Overview

This DevRev helper is mostly coherent, but it gives an agent broad token-backed authority to modify live DevRev data without clear confirmation or safety boundaries.

Install only if you are comfortable letting the agent use a DevRev token for the DevRev workspace. Use a dedicated least-privilege token, avoid pasting the token into chat, verify object IDs and fields before any write, and require explicit confirmation for create, update, or delete actions.

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)

Vague Triggers

Medium
Confidence
87% confidence
Finding
The skill trigger is broad enough to activate on generic DevRev-related requests, which increases the chance the agent will invoke this skill and perform sensitive remote actions without sufficiently narrow user intent matching. In a skill that can create and update tickets and issues, overbroad routing materially raises the risk of unintended external side effects.

Missing User Warnings

Medium
Confidence
93% confidence
Finding
The documentation includes create and update operations against a live external service without prominently warning that these commands modify remote DevRev data. In an agent setting, this omission makes accidental or premature state-changing actions more likely, especially when the skill is used from natural-language prompts.

Missing User Warnings

Medium
Confidence
91% confidence
Finding
The skill instructs use of a personal access token but does not include guidance on secure credential handling, scope minimization, or avoiding disclosure in logs and prompts. Because the token authorizes access to a remote DevRev workspace, poor handling could expose sensitive project data or enable unauthorized modifications.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal