fiftyone-develop-plugin
Pass
Audited by Gen Agent Trust Hub on Oct 17, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADSCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill's primary function is to transform user prompts into plugin code and execute development commands, which creates a surface for indirect prompt injection.
- Ingestion points: User requirements for plugin functionality and UI design provided as natural language prompts in
SKILL.md. - Boundary markers: Directives in
SKILL.mdinstruct the agent to ask clarifying questions and present a plan for user approval before generating any code. - Capability inventory: The skill has the capability to write files, clone repositories via
git clone, and execute commands such asnpm,vite, andpytestas described inSKILL.md,HYBRID-PLUGINS.md, andPYTHON-OPERATOR.md. - Sanitization: No explicit sanitization or filtering of user-provided content is mentioned before it is incorporated into the generated code.
- [EXTERNAL_DOWNLOADS]: The skill provides instructions to download reference implementations from a remote repository.
- Evidence:
SKILL.mdincludes commands to clone the official plugin repository fromgithub.com/voxel51/fiftyone-plugins.gitfor pattern reference. - [COMMAND_EXECUTION]: The skill utilizes various system and development tools to manage the plugin lifecycle.
- Evidence: Instructions involve the use of
git,npm,npx playwright,pytest, andln -sfor environment setup, building, and testing, as seen inSKILL.mdandHYBRID-PLUGINS.md.
Audit Metadata