find-connections
Pass
Audited by Gen Agent Trust Hub on Sep 1, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [COMMAND_EXECUTION]: The skill is instructed to execute a local binary located at .slipbox/bin/slipbox to find and record link relationships.
- [INDIRECT_PROMPT_INJECTION]: The skill reads literature and evergreen notes which are untrusted data sources.
- Ingestion points: Reads content from vault notes, specifically literature and evergreen note files.
- Boundary markers: Lacks explicit delimiters or markers to isolate note content from instructions.
- Capability inventory: Executes the local binary .slipbox/bin/slipbox and can invoke other skills such as make-reference-note or make-literature-note.
- Sanitization: No specific sanitization or validation of note content is described before use in clustering or classification.
Audit Metadata