bot-jobs
Pass
Audited by Gen Agent Trust Hub on Apr 10, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill manages a registry of tasks that include prompt instructions intended for future execution.
- Ingestion points: Reads job definitions, including prompt text, from
JOBS.yamllocated in the$PILOT_BOT_DIRdirectory. - Boundary markers: No delimiters or instructions are used to distinguish the stored prompt from the agent's operational logic.
- Capability inventory: The skill uses the
CronCreateandCronDeletetools to manage the execution lifecycle of these prompts. - Sanitization: There is no evidence of validation or sanitization of the
promptfield before it is provided to the execution tools.
Audit Metadata