semantic-gap-analysis
Pass
Audited by Gen Agent Trust Hub on Aug 12, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection via untrusted data sources. Ingestion points: The agent fetches user-provided URLs and competitor pages from Google search results. Boundary markers: There are no instructions to the agent to treat the fetched content as untrusted or to ignore embedded commands. Capability inventory: The agent uses search and browsing tools to retrieve text, then analyzes it and suggests passing results to other skills. Sanitization: No sanitization or filtering is performed on the data retrieved from the internet.
Audit Metadata