read-topic-collector

Pass

Audited by Gen Agent Trust Hub on Jul 11, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill is a legitimate tool for aggregating AI-related news and research. It uses standard web search queries to collect information from well-known platforms.
  • [PROMPT_INJECTION]: The skill presents a surface for indirect prompt injection by processing untrusted data from external websites.
  • Ingestion points: Content retrieved via WebSearch from various social media and news sites.
  • Boundary markers: None present.
  • Capability inventory: The skill is limited to reading search results and producing structured markdown; it lacks capabilities for file system modification, network exfiltration, or code execution.
  • Sanitization: There is no evidence of specific sanitization for ingested content, which is standard for summarization tasks.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 11, 2026, 03:51 PM
Security Audit — agent-trust-hub — read-topic-collector