drupal-config-mgmt
Pass
Audited by Gen Agent Trust Hub on Mar 20, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill provides templates and instructions for executing shell commands via ssh, drush, ddev, and git. These commands are used to inspect, retrieve, and manage Drupal configuration files across different environments.
- [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection as it processes untrusted configuration data from remote servers.
- Ingestion points: Data is ingested from remote servers using commands like 'drush config:get' executed over SSH (documented in SKILL.md and references/full-guide.md).
- Boundary markers: No specific delimiters or instructions to ignore embedded content are used when the agent processes the retrieved configuration values.
- Capability inventory: The skill utilizes shell command execution (ssh, git, drush, rm), filesystem access (reading/writing to /tmp and local config directories), and the Edit tool.
- Sanitization: There is no evidence of sanitization or strict schema validation for the external configuration data before it is read by the agent or committed to the local repository.
Audit Metadata