drupal-contrib-mgmt

Pass

Audited by Gen Agent Trust Hub on Apr 17, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill instructs the agent to fetch and apply patches from official Drupal infrastructure.
  • Evidence: SKILL.md and examples/find-and-apply-patch.sh describe downloading .patch and .diff files from drupal.org and git.drupalcode.org.
  • [COMMAND_EXECUTION]: Utilizes standard CLI tools for development and project management.
  • Evidence: Various scripts and SKILL.md demonstrate the use of composer for dependency management, drush for Drupal site operations, and git for version control and patch creation.
  • [PROMPT_INJECTION]: The skill instructions for researching issues and monitoring RSS feeds represent an indirect prompt injection surface (Category 8).
  • Ingestion points: RSS feeds from drupal.org (references/issue-queue-rss-feeds.md) and issue descriptions/comments on the Drupal issue queue (examples/find-and-apply-patch.sh).
  • Boundary markers: Absent; there are no specific instructions to use delimiters or ignore instructions embedded in the external content.
  • Capability inventory: The skill has the capability to modify the filesystem (cat, git diff), manage dependencies (composer), and execute database updates (drush updb).
  • Sanitization: Absent; external user-generated content is processed directly for triage and research purposes.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 17, 2026, 10:42 AM
Security Audit — agent-trust-hub — drupal-contrib-mgmt