news-monitoring

Pass

Audited by Gen Agent Trust Hub on Aug 15, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [COMMAND_EXECUTION]: The skill uses curl and the ddgs utility to fetch data from search engines and RSS feeds. It also references a local Python helper script within the platform's internal skill directory to support extended API functionality.
  • [PROMPT_INJECTION]: The skill is an ingestion point for untrusted external data retrieved from the web.
  • Ingestion points: Search results and RSS feed content retrieved via the web_search tool, curl commands, and the ddgs library.
  • Boundary markers: Absent. The skill instructions do not specify explicit delimiters to isolate external content from the agent's instructions.
  • Capability inventory: The skill uses web_search, shell-based data retrieval (curl), and the cronjob tool for automation.
  • Sanitization: Includes instructions for quality filtering and deduplication based on metadata (titles and dates), which provides a basic level of content selection.
  • [EXTERNAL_DOWNLOADS]: The skill retrieves news content and search results from external sources. These downloads are a core part of the news monitoring workflow and target well-known or user-defined services.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 15, 2026, 06:15 PM
Security Audit — agent-trust-hub — news-monitoring