Ai Daily Report

• Outcome: Pass
• Latest audit: May 29, 2026 at 8:32 PM UTC
• Version:
  1.0.0

Overview

This skill matches its stated purpose of generating an AI news report and sending it to Feishu, with some credential and third-party-service privacy points to review.

Install only if you want automated AI news reports that can be uploaded to Feishu. Use a limited GitHub token, verify FEISHU_CHAT_ID before enabling cron or HEARTBEAT scheduling, and avoid feeding private project descriptions into the report unless you accept possible translation through googletrans.

SkillSpector

By NVIDIA

Vulnerability Patterns

• Data Exfiltration: External Transmission, Env Variable Harvesting, File System Enumeration
• MCP Least Privilege: Underdeclared Capability, Wildcard Permission, Missing Permission Declaration
• 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

Findings (4)

Lp3

Medium

• Category: MCP Least Privilege
• Confidence: 91% confidence
• Finding: The skill declares and documents capabilities to read environment variables, access the network, write files, and invoke shell-based converters, but no explicit permission model is declared. That creates an overbroad and opaque execution surface: operators or users may trigger a skill that can access secrets and send data externally without clear authorization boundaries.

Missing User Warnings

Medium

• Confidence: 95% confidence
• Finding: The skill supports automatic outbound delivery of generated content to Feishu, including scheduled execution that can send to a preset chat ID, but the description does not prominently warn users about this exfiltration-like behavior. In practice, this can cause unintended disclosure of generated content, metadata, or future expanded inputs to external recipients without an interactive confirmation step.

Missing User Warnings

Low

• Confidence: 87% confidence
• Finding: The skill requires a GitHub access token but does not warn about credential handling, storage, or scope minimization. Even if only used for API access, undocumented token practices increase the chance of overscoped tokens, insecure storage, or accidental exposure through logs or environment reuse.

Missing User Warnings

Medium

• Confidence: 90% confidence
• Finding: Project descriptions are automatically transmitted to an external translation service through googletrans without user notice, consent, or data-classification checks. In a scheduled reporting skill, this can silently exfiltrate third-party or internally curated content to an outside service, creating privacy, compliance, and supply-chain risk.

VirusTotal

66/66 vendors flagged this skill as clean.