task-context-loader

Pass

Audited by Gen Agent Trust Hub on Mar 10, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill uses the ls command to retrieve a list of active tasks from the implementation_process/in_progress/ directory. This operation is used for task discovery and is benign.
  • [PROMPT_INJECTION]: The skill possesses an indirect prompt injection surface as it reads and processes content from various project files.
  • Ingestion points: Reads task.md, research.md, architecture.md, implementation.md, and Drupal core files.
  • Boundary markers: No explicit delimiters or instructions to ignore embedded commands are used in the file loading steps.
  • Capability inventory: The skill performs file reading and directory listing.
  • Sanitization: No sanitization is applied to the content retrieved from external files.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 10, 2026, 12:30 AM