drupal-project-description

Pass

Audited by Gen Agent Trust Hub on Jul 23, 2026

Risk Level: SAFE
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill uses curl to fetch project page content from drupal.org. This is a well-known service, and the download is used solely for extracting existing description text to facilitate editing.
  • [COMMAND_EXECUTION]: Employs standard shell commands to download data and write HTML files to the local project directory. These actions are consistent with the skill's stated purpose of managing project documentation.
  • [PROMPT_INJECTION]: The skill processes data from external web pages, which introduces a surface for indirect prompt injection.
  • Ingestion points: Content downloaded from drupal.org/project/ into a local page.html file.
  • Boundary markers: No explicit delimiters are used to separate the external content from system instructions during processing.
  • Capability inventory: Shell command execution for data retrieval, file system write access, and potential browser-based screenshot functionality.
  • Sanitization: Output is limited to a strict whitelist of HTML tags and specific CSS classes allowed by the Drupal.org platform.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 23, 2026, 09:39 AM
Security Audit — agent-trust-hub — drupal-project-description