Bugherd

• Outcome: Review
• Latest audit: May 29, 2026 at 9:36 PM UTC
• Version:
  1.0.4

Overview

This is a coherent BugHerd integration, but it gives an agent broad authenticated ability to change BugHerd data and make raw API requests without clear approval boundaries.

Install only if you are comfortable granting an agent authenticated BugHerd access through Membrane. Use a least-privileged BugHerd account where possible, require explicit approval before create, update, delete, webhook, or raw proxy API calls, review the exact target project/task and request body, and revoke the connection when no longer needed.

SkillSpector

By NVIDIA

Vulnerability Patterns

• Prompt Injection: Instruction Override, Hidden Instructions, Exfiltration Commands
• Data Exfiltration: External Transmission, Env Variable Harvesting, File System Enumeration
• Privilege Escalation: Excessive Permissions, Sudo/Root Execution, Credential Access
• Supply Chain: Unpinned Dependencies, External Script Fetching, Obfuscated Code
• Excessive Agency: Unrestricted Tool Access, Autonomous Decision Making, Scope Creep

Findings (1)

Missing User Warnings

Medium

• Confidence: 93% confidence
• Finding: The skill documents create, update, and proxy-request capabilities without explicit guardrails requiring user confirmation before state-changing actions. In an agent setting, this can lead to unintended modifications to BugHerd projects, tasks, comments, or webhooks if the model infers permission from ambiguous user requests.

VirusTotal

63/63 vendors flagged this skill as clean.