datocms-feedback
Pass
Audited by Gen Agent Trust Hub on Sep 28, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill instructs the agent to execute system-level commands (
open,xdg-open, orstart) to launch a web browser with a constructed URL. This is a functional requirement for the skill's purpose of opening a support page. - [INDIRECT_PROMPT_INJECTION]: The skill ingests conversation context to populate the feedback form, which introduces a theoretical vulnerability if the processed content contains malicious instructions.
- Ingestion points: The skill reads attempted goals, runtime context, and error excerpts from the active session in
SKILL.md. - Boundary markers: No specific delimiters are defined for the interpolated data within the URL string, although the skill requires parameters to be URL-encoded.
- Capability inventory: The skill has the ability to execute shell commands to open the browser as defined in
SKILL.md. - Sanitization: The skill contains explicit instructions to exclude secrets, tokens, private content, and user-identifying details from the feedback body.
Audit Metadata