logseq-schema
Pass
Audited by Gen Agent Trust Hub on Oct 9, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill provides detailed instructions and examples for using the
logseqcommand-line interface to perform graph queries, data inspection, and schema discovery. - [INDIRECT_PROMPT_INJECTION]: The skill provides methods to ingest and process data from external Logseq databases, which serves as an attack surface for indirect prompt injection if the database content is untrusted.
- Ingestion points: Data is retrieved via
logseq queryandlogseq showcommands as described inreferences/logseq-datascript-query-examples.md. - Boundary markers: The instructions do not define specific delimiters or warnings to separate data retrieved from the database from the agent's internal instructions.
- Capability inventory: The skill documentation defines read-only patterns for querying the database; it does not include scripts with write access or network capabilities.
- Sanitization: There are no instructions for sanitizing or validating the content retrieved from the database before it is processed by the agent.
Audit Metadata