news-monitor

Pass

Audited by Gen Agent Trust Hub on Jun 13, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill uses uvx to execute the web-forager package and uv run to execute a Python script utilizing the ddgs library. These commands are used to perform news searches as part of the skill's primary function.
  • [EXTERNAL_DOWNLOADS]: The skill fetches article content from external websites via the r.jina.ai markdown conversion service using curl. Jina AI is a well-known service for this purpose.
  • [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection as it retrieves and processes untrusted content from the web.
  • Ingestion points: News article snippets and full text content retrieved from external URLs (SKILL.md).
  • Boundary markers: No explicit markers are used to delimit external content from the prompt instructions.
  • Capability inventory: Subprocess execution via uvx, uv run, and curl for searching and fetching content (SKILL.md).
  • Sanitization: No content validation or escaping is specified before the AI processes the data.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 13, 2026, 01:24 AM
Security Audit — agent-trust-hub — news-monitor