kore
Pass
Audited by Gen Agent Trust Hub on Oct 7, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill executes shell commands using the
koreCLI. Specifically, thekore ingestcommand pattern (echo "content" | kore ingest) is a potential command injection surface if the environment does not properly escape the content being piped into the shell.- [INDIRECT_PROMPT_INJECTION]: The skill processes data from an external personal knowledge base that could contain malicious instructions from external sources (e.g., saved bookmarks or notes). - Ingestion points: Data enters the context via
kore search,kore show, andkore insightscommands. - Boundary markers: There are no explicit instructions to use delimiters or ignore instructions found within the retrieved content.
- Capability inventory: The skill can execute CLI commands, read data from the local memory bank, and ingest new content.
- Sanitization: No validation or sanitization steps are defined for the data retrieved from the knowledge base before it is synthesized or presented to the user.
Audit Metadata