aituber-api

Fail

Audited by Gen Agent Trust Hub on Sep 2, 2026

Risk Level: CRITICALDATA_EXFILTRATIONINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADSCOMMAND_EXECUTION
Full Analysis
  • [DATA_EXFILTRATION]: The skill transmits the AITUBER_API_KEY and user-provided scripts to the external vendor domain app.aituber.app. This is a standard vendor communication pattern for this service.
  • [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted user content, providing a vector for indirect prompt injection.
  • Ingestion points: User-provided strings for script and prompt parameters in SKILL.md.
  • Boundary markers: No delimiters are defined to isolate user input from the agent context.
  • Capability inventory: The skill uses Bash(curl:*), WebFetch, Read, and Write tools.
  • Sanitization: No input sanitization is described.
  • [EXTERNAL_DOWNLOADS]: The skill references external vendor resources, including a GitHub repository (aituberapp/aituber-mcp) and an NPM package (@aituber/mcp-server).
  • [COMMAND_EXECUTION]: The skill executes curl commands to interact with the API, as permitted by its configuration.
Recommendations
  • CRITICAL: 1 file(s) identified as malware by FileRep - DO NOT USE
  • Contains 22 malicious URL(s) - DO NOT USE
Audit Metadata
Risk Level
CRITICAL
Analyzed
Sep 2, 2026, 06:25 AM
Security Audit — agent-trust-hub — aituber-api