e-bookkeeping-compliance
Pass
Audited by Gen Agent Trust Hub on Sep 18, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill invokes the
shinkokucommand-line utility with multiple sub-commands such asledger trial-balance,ledger search, andledger audit-logto process financial data based on user input. - [INDIRECT_PROMPT_INJECTION]: The skill has an attack surface for indirect instructions through local files and tool outputs.
- Ingestion points: Reads the contents of
docs/system-overview.mdand parses the output of variousshinkokucommands in SKILL.md. - Boundary markers: None present; the skill does not use specific delimiters to protect against malicious instructions embedded in the ingested data.
- Capability inventory: Shell command execution via the
shinkokutool as defined in SKILL.md. - Sanitization: The instructions do not specify validation or sanitization for the user-provided
--db-pathparameter before it is interpolated into shell commands.
Audit Metadata