trending-topic-radar

Pass

Audited by Gen Agent Trust Hub on Jun 20, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: No malicious instructions, obfuscation, or unauthorized actions were detected in the skill file.- [DATA_EXFILTRATION]: No exfiltration of sensitive data or access to private files was found. The skill's data gathering is limited to public web searches via the platform's search tool.- [PROMPT_INJECTION]: The skill demonstrates a standard surface for indirect prompt injection due to its processing of external web content, but no specific vulnerabilities were identified.
  • Ingestion points: External data is ingested from web search results via 'search_web' in SKILL.md.
  • Boundary markers: No explicit boundary markers or delimiters are used for the external data.
  • Capability inventory: Uses 'search_web' for information retrieval and local file writing in SKILL.md.
  • Sanitization: Relies on standard agent processing without explicit sanitization logic.- [COMMAND_EXECUTION]: Interaction with the file system is limited to writing reports into a dedicated './选题方案/' directory, which aligns with the tool's intended purpose of generating content plans.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 20, 2026, 02:56 PM
Security Audit — agent-trust-hub — trending-topic-radar