sun-yuchen-perspective

Pass

Audited by Gen Agent Trust Hub on Apr 15, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill is vulnerable to Indirect Prompt Injection as it explicitly mandates the use of external search tools to gather real-time information, which is then processed by the agent.
  • Ingestion points: External data enters the agent's context through the WebSearch tool, as instructed in the 'Agentic Protocol' section of SKILL.md.
  • Boundary markers: The instructions do not define boundary markers (such as XML tags or specific delimiters) or provide warnings to ignore embedded instructions within the search results.
  • Capability inventory: The agent is instructed to use tools to search for project narratives, market data, and social trends across the web.
  • Sanitization: No sanitization or validation logic is provided to filter malicious content or instructions from the retrieved data before processing.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 15, 2026, 05:21 AM
Security Audit — agent-trust-hub — sun-yuchen-perspective