daily-task-prep
Pass
Audited by Gen Agent Trust Hub on Oct 7, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill aggregates data from external sources including calendar attendee brain pages, timeline entries, and Google-sourced threads.
- Ingestion points: Attendee brain pages, recent timeline, and
gbrain waitingJSON output (SKILL.md). - Boundary markers: The instructions do not define delimiters or instruct the agent to ignore embedded instructions within the ingested data.
- Capability inventory: The skill utilizes
search,query, and thegbrainCLI tool to fetch and process data. - Sanitization: There is no evidence of sanitization, escaping, or filtering for external content before it is interpolated into the agent's context.
- [COMMAND_EXECUTION]: The skill uses the
gbraincommand-line utility (e.g.,gbrain waiting --json) to retrieve data about open threads. - Potential Risk: If meeting titles, attendee names, or task descriptions containing shell metacharacters are passed as arguments to the
gbraintool or subsequent commands without proper validation, it could facilitate command injection.
Audit Metadata