newscatcher

Pass

Audited by Gen Agent Trust Hub on Apr 29, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill utilizes the membrane CLI for connection management and action execution, which is the platform's standard operational mode.
  • [EXTERNAL_DOWNLOADS]: The skill involves downloading and installing the @membranehq/cli package from NPM, which is an official resource belonging to the skill's vendor.
  • [PROMPT_INJECTION]: The skill processes news content from NewsCatcher, which constitutes an indirect prompt injection surface. Ingestion points: Article text and summaries (SKILL.md). Boundary markers: Absent. Capability inventory: Running CLI-based actions (SKILL.md). Sanitization: Not explicitly defined. This ingestion is necessary for the skill's primary function of news aggregation.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 29, 2026, 05:38 PM
Security Audit — agent-trust-hub — newscatcher