newsapi

Pass

Audited by Gen Agent Trust Hub on Mar 15, 2026

Risk Level: SAFEPROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [PROMPT_INJECTION]: The skill retrieves and processes news articles from third-party publishers, establishing a potential surface for indirect prompt injection.
  • Ingestion points: News headlines and article bodies fetched via get-top-headlines and search-everything actions in SKILL.md.
  • Boundary markers: The skill does not provide instructions to the agent to use delimiters or specifically ignore instructions embedded within the news content.
  • Capability inventory: The agent is authorized to execute membrane CLI commands for further actions and proxy requests based on findings.
  • Sanitization: No sanitization or validation mechanisms are defined for the external news data.
  • [EXTERNAL_DOWNLOADS]: The skill requires the installation of a global NPM package for functionality.
  • Evidence: npm install -g @membranehq/cli in SKILL.md.
  • Note: The package is the official CLI tool provided by the vendor (@membranehq) and is considered a trusted dependency in this context.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 15, 2026, 03:53 PM