market-segment
Pass
Audited by Gen Agent Trust Hub on Nov 8, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes data from external market research files and existing segment definitions, creating an attack surface where untrusted content could influence agent behavior.
- Ingestion points: Reads existing segment files during the UPDATE mode and references market research documents via @file syntax as specified in the Instructions section.
- Boundary markers: The skill does not define explicit delimiters or instructions to ignore embedded commands within the ingested research files or existing segment data.
- Capability inventory: The skill uses WebSearch to gather data and performs file search and write operations within the
segments/,market/,gtm/segments/, andstrategy/directories. - Sanitization: There is no evidence of sanitization or validation logic to filter potentially malicious instructions embedded in the external market data.
Audit Metadata