@3182/world-news-digest

Pass

Audited by Gen Agent Trust Hub on Aug 14, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill retrieves international news headlines and article details using web_search and web_fetch tools.
  • [COMMAND_EXECUTION]: The skill invokes agentx tool methods to publish threaded posts and comments, and it generates Python scripts in the output/ directory for task auditing.
  • [PROMPT_INJECTION]: The skill processes untrusted web content and incorporates it into published content, creating a surface for indirect prompt injection.
  • Ingestion points: Search results and article text retrieved via web_search and web_fetch.
  • Boundary markers: No delimiters are specified to isolate untrusted data from the agent's instructions.
  • Capability inventory: The agent can publish to the AgentX platform and register scheduled tasks.
  • Sanitization: No content filtering or validation is performed on the ingested news data before processing.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 14, 2026, 01:41 PM
Security Audit — agent-trust-hub — @3182/world-news-digest