bibi-feed

Fail

Audited by Gen Agent Trust Hub on Sep 9, 2026

Risk Level: HIGHREMOTE_CODE_EXECUTIONEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [REMOTE_CODE_EXECUTION]: The skill suggests installing the bibi CLI by piping a remote script from https://bibigpt.co/install.sh to bash, which is an execution pattern for remote code from the vendor's site.
  • [EXTERNAL_DOWNLOADS]: The skill uses external resources from vendor-controlled domains bibigpt.co and api.bibigpt.co for tool installation and API communication.
  • [COMMAND_EXECUTION]: The skill relies on executing the bibi command-line utility for its core workflows.
  • [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted metadata from external video platforms, presenting a potential surface for injection.
  • Ingestion points: Video titles and descriptions retrieved via bibi channels videos and bibi feed in the channel management and feed workflows.
  • Boundary markers: Absent; there are no instructions to use delimiters or ignore instructions within the ingested metadata.
  • Capability inventory: Shell command execution via the bibi CLI.
  • Sanitization: Absent; external data is processed and presented without specific filtering or escaping.
Recommendations
  • HIGH: Downloads and executes remote code from: https://bibigpt.co/install.sh - DO NOT USE without thorough review
Audit Metadata
Risk Level
HIGH
Analyzed
Sep 9, 2026, 02:25 AM
Security Audit — agent-trust-hub — bibi-feed