daily-xhs-content

Pass

Audited by Gen Agent Trust Hub on Apr 23, 2026

Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill executes local shell commands and scripts to manage content workflows, including directory creation (mkdir), searching via search.js, image generation with relay_image_gen.py, and draft publishing via publish.py.- [INDIRECT_PROMPT_INJECTION]: The skill ingests data from external search results to identify trends, creating a surface for potential indirect instruction injection.
  • Ingestion points: Web content retrieved via the Brave Search skill in Step 1.
  • Boundary markers: No specific delimiters are used to wrap the ingested search content.
  • Capability inventory: Includes directory creation (mkdir), file writing, and script execution (python3, uv run).
  • Sanitization: The skill implements a mandatory multi-step quality check (Step 4) and specifies that final publication is subject to manual human review.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 23, 2026, 05:42 AM