schedule
Pass
Audited by Gen Agent Trust Hub on Mar 15, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [SAFE]: The skill is designed for schedule management and uses local resources appropriately. No malicious patterns such as obfuscation, exfiltration, or unauthorized remote code execution were found.
- [COMMAND_EXECUTION]: The
scripts/calendar.tsfile executes the systemcalcommand to format calendar data. The input parameters (month and year) are generated from the system's current date, which mitigates the risk of command injection. - [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection as it ingests untrusted data from an external API and local files.
- Ingestion points: Data is fetched from
GET /api/scheduleinscripts/query.tsand read fromschedule.mdinscripts/calendar.ts. - Boundary markers: Absent. The output is rendered directly into the agent context without delimiters or warnings.
- Capability inventory: The skill facilitates network requests to the local API and reads local files via Bun scripts.
- Sanitization: Absent. Event names, notes, and other fields from the API or file are not sanitized for potential instructions.
Audit Metadata