positioning-and-messaging
Pass
Audited by Gen Agent Trust Hub on Oct 7, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process untrusted data from external sources, which presents a surface for potential indirect prompt injection attacks.
- Ingestion points: The skill processes user-provided customer conversation transcripts and utilizes a web search tool to analyze live competitor marketing materials.
- Boundary markers: The instructions do not define specific delimiters or isolation techniques (such as XML tags or unique markers) to clearly separate untrusted external content from the agent's core instructions.
- Capability inventory: The skill has access to a web search tool to perform live market analysis.
- Sanitization: There are no explicit instructions for the AI to sanitize, validate, or ignore potentially malicious instructions embedded within the analyzed transcripts or web pages.
Audit Metadata