Feishu Webhook

• Outcome: Pass
• Latest audit: May 28, 2026 at 11:01 AM UTC
• Version:
  1.2.4

Overview

This is a straightforward Feishu webhook sender; it sends provided text to Feishu, which matches its stated purpose.

Install only if you want an agent or user command to post supplied content to Feishu. Verify the webhook points to the intended channel or DM, keep the webhook URL and secret out of source control, and do not pass secrets, personal data, or private reports unless they are meant to appear in that Feishu destination.

SkillSpector

By NVIDIA

Vulnerability Patterns

• Data Exfiltration: External Transmission, Env Variable Harvesting, File System Enumeration
• Prompt Injection: Instruction Override, Hidden Instructions, Exfiltration Commands
• 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 (3)

Missing User Warnings

Medium

• Confidence: 90% confidence
• Finding: The README instructs users to send arbitrary Markdown content to an external Feishu webhook but does not clearly warn that message contents will leave the local environment and be transmitted to a third-party service. In an agent-skill context, this can lead to accidental disclosure of sensitive reports, secrets, or internal data because users may treat the skill as a local formatting utility rather than a networked exfiltration path.

Missing User Warnings

Medium

• Confidence: 92% confidence
• Finding: The documentation instructs users to pipe arbitrary Markdown content into a script that sends it to a Feishu webhook, but it does not clearly warn that all provided content will leave the local environment and be delivered to an external third-party service. In agent settings, this creates a real risk of accidental data exfiltration if sensitive prompts, reports, or secrets are passed through the heredoc.

Missing User Warnings

Medium

• Confidence: 84% confidence
• Finding: The script reads arbitrary stdin content and transmits it to a remote Feishu webhook with no confirmation, content classification, or warning that input will leave the local environment. In agent workflows, this can cause accidental disclosure of secrets, internal reports, or sensitive prompt/context data if upstream components pipe unreviewed content into the skill.

VirusTotal

66/66 vendors flagged this skill as clean.