pachca-forms
Pass
Audited by Gen Agent Trust Hub on Mar 17, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill uses
npx @pachca/clito fetch and execute the vendor's official command-line tool from the npm registry. - [COMMAND_EXECUTION]: Uses Bash commands (
pachca,npx) to perform API operations such as creating messages, opening form views, and managing tasks. - [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection (Category 8) due to its handling of external data.
- Ingestion points: Processes webhook event data including
trigger_id,callback_id, and form submission content (data) as described inSKILL.mdandreferences/handle-form-submission-viewsubmission.md. - Boundary markers: No boundary markers or instructions to disregard embedded commands were found in the provided templates.
- Capability inventory: The skill possesses the capability to execute shell commands (
pachca views open,pachca messages create, etc.) that incorporate data from external sources. - Sanitization: There is no evidence of input validation or sanitization being performed on the webhook data before it is used in CLI command arguments.
Audit Metadata