product-competitor-intelligence
Pass
Audited by Gen Agent Trust Hub on Jul 17, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: Indirect Prompt Injection Surface\n
- The skill facilitates extensive web research, creating a surface for indirect prompt injection where malicious instructions could be embedded in the content of competitor websites, retailer listings, or marketplaces processed by the agent.\n
- Ingestion points: External data is retrieved from various websites and catalogs via search, crawl, and extract capabilities (SKILL.md).\n
- Boundary markers: Absent. The skill does not provide instructions or delimiters to help the agent distinguish untrusted research data from its core system instructions.\n
- Capability inventory: The agent leverages web searching, mapping, crawling, and data extraction to gather market intelligence and synthesize reports (SKILL.md).\n
- Sanitization: Absent. There is no logic described for validating or sanitizing retrieved content before it is incorporated into the agent's context and final output.
Audit Metadata