fairstack-workflows
Pass
Audited by Gen Agent Trust Hub on Mar 23, 2026
Risk Level: SAFEPROMPT_INJECTIONEXTERNAL_DOWNLOADSCOMMAND_EXECUTION
Full Analysis
- [PROMPT_INJECTION]: The skill implements a workflow system that interpolates user-provided variables into node prompts (e.g., {{subject}}). This creates a surface for indirect prompt injection where untrusted data could influence the behavior of generation nodes.
- Ingestion points: The variables object in the workflow execution request (SKILL.md).
- Boundary markers: No explicit delimiters or instructions to ignore embedded commands are present in the prompt templates.
- Capability inventory: The skill can trigger automated image, video, and voice generation via authenticated API calls to fairstack.ai.
- Sanitization: No input validation or sanitization of the variable content is mentioned.
- [EXTERNAL_DOWNLOADS]: The skill references the @fairstack/sdk Node.js package. This is a vendor-owned resource used to interface with the FairStack API.
- [COMMAND_EXECUTION]: Documentation provides curl examples and shell commands for environment variable configuration, which are standard for developer-facing API skills.
Audit Metadata