spreadsheet-automation
Pass
Audited by Gen Agent Trust Hub on Jun 18, 2026
Risk Level: SAFEPROMPT_INJECTIONNO_CODE
Full Analysis
- [PROMPT_INJECTION]: The skill describes a workflow (Workflow 1 in SKILL.md) that ingests untrusted data from an external Typeform webhook into an AI prompt for sentiment analysis. This creates a surface for indirect prompt injection, where an external user could craft feedback to manipulate the model's classification or influence downstream automation actions like Slack alerts. Ingestion points: Customer feedback field in the Typeform payload. Boundary markers: Simple text labels (e.g., 'Feedback:') provide minimal protection against adversarial input. Capability inventory: The AI's output is used to determine conditional logic for sending Slack messages and emails. Sanitization: No explicit sanitization or validation of the input text is described in the provided workflows.
- [NO_CODE]: The skill consists entirely of markdown documentation and JSON examples. It does not contain any executable scripts, binary files, or configuration that would lead to code execution in the agent's local environment.
Audit Metadata