pachca-forms
Pass
Audited by Gen Agent Trust Hub on Mar 7, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill utilizes the Bash tool with
curlto interact with the official Pachca API athttps://api.pachca.com/api/shared/v1. This is the primary method for opening views and managing form interactions. - [PROMPT_INJECTION]: An indirect prompt injection surface is identified as the skill processes external data originating from user interactions with the forms.
- Ingestion points: The
datafield within theview_submissionwebhook payload (referenced inSKILL.md) contains arbitrary user input. - Boundary markers: No specific delimiters or instructions to ignore embedded commands within the form data are implemented.
- Capability inventory: The skill has access to the
Bash(curl *)tool to make network requests. - Sanitization: The skill description does not specify any sanitization or validation of the values received in the
datafield before they are processed or used in subsequent API calls.
Audit Metadata