publish-moviepilot-plugin

Pass

Audited by Gen Agent Trust Hub on Sep 9, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill executes a local Python script scripts/publish_plugin.py using execute_command to perform GitHub operations, repository management, and local file comparison.
  • [EXTERNAL_DOWNLOADS]: Synchronizes plugin files and metadata from GitHub repositories via the GitHub Contents API during pull, push, and preview operations.
  • [INDIRECT_PROMPT_INJECTION]: The skill processes plugin metadata (package.json) and file content from external GitHub repositories, creating a surface for indirect instructions to enter the agent context.
  • Ingestion points: Downloads file content and metadata from GitHub repositories within scripts/publish_plugin.py.
  • Boundary markers: Not explicitly mentioned in instructions, though the skill primarily treats the data as files to be synchronized rather than instructions to be executed.
  • Capability inventory: The skill has access to execute_command, write_file, and moviepilot_api for local system modifications.
  • Sanitization: The script uses JSON parsing for metadata validation and handles file content as binary data.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 9, 2026, 03:49 AM
Security Audit — agent-trust-hub — publish-moviepilot-plugin