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
WebSearchtool, as instructed in the 'Agentic Protocol' section ofSKILL.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