cgenius
Pass
Audited by Gen Agent Trust Hub on Oct 16, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted data through several entry points, creating a potential surface for indirect prompt injection attacks.
- Ingestion points: Data from client questionnaires (/cgenius questionnaire), market research results (/cgenius offer research), and content ideation analysis (/cgenius ideate analyze) are processed by the agent.
- Boundary markers: There are no explicit instructions or delimiters defined to separate user/agent instructions from the data fetched or received from external participants.
- Capability inventory: The skill has the capability to generate and publish content, send emails, and create presentations based on the processed data.
- Sanitization: The instructions do not specify any validation or sanitization steps for data received from the questionnaire system or research APIs before it is incorporated into the agent's context.
Audit Metadata