schedule
Pass
Audited by Gen Agent Trust Hub on Apr 9, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The script
scripts/calendar.tsuses Bun's shell API to run the systemcalcommand. While the parameters are constrained to dates, shell execution is a high-privilege capability. - [PROMPT_INJECTION]: The skill processes external data that could contain malicious instructions for the agent (Category 8).
- Ingestion points: Reads from
~/.oracle/ψ/inbox/schedule.mdand a local API athttp://localhost:47778. - Boundary markers: None. The agent receives the schedule data without delimiters or warnings to ignore embedded instructions.
- Capability inventory: The skill can execute scripts, run shell commands, and make network requests.
- Sanitization: Event content is parsed and displayed without sanitization or validation.
Audit Metadata