cognee-server
Pass
Audited by Gen Agent Trust Hub on Oct 18, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill establishes an interface for the agent to query and retrieve data from a Cognee memory server, creating a potential vector for indirect prompt injection if the retrieved content contains adversarial instructions.
- Ingestion points: Untrusted data enters the agent's context via HTTP responses from memory-related API routes such as
/api/v1/recall,/api/v1/search, andsessionsdescribed inSKILL.md. - Boundary markers: The instructions do not specify the use of delimiters or 'ignore embedded instructions' prompts when handling data returned from the server.
- Capability inventory: The skill uses the
cognee-cliandcogneePython SDK to execute memory operations and visualization tasks (SKILL.md). - Sanitization: The document does not describe any validation or escaping mechanisms for the data retrieved from the external server before it is processed by the agent.
Audit Metadata