competitor-offer-analysis
Pass
Audited by Gen Agent Trust Hub on Jun 29, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill is susceptible to Indirect Prompt Injection because it is designed to ingest and analyze content from external, untrusted competitor URLs.
- Ingestion points: The
competitorsinput field inSKILL.mdaccepts a list of URLs that the agent is expected to visit and analyze. - Boundary markers: The instructions do not specify the use of delimiters or 'ignore' instructions to prevent the agent from obeying commands found on external websites.
- Capability inventory: The agent reads external web content and processes it to generate positioning recommendations.
- Sanitization: There is no mention of sanitizing or escaping the content retrieved from external URLs before it is processed by the model.
Audit Metadata