kelly-standup
Pass
Audited by Gen Agent Trust Hub on Aug 25, 2026
Risk Level: SAFE
Full Analysis
- [DATA_EXPOSURE_AND_EXFILTRATION]: The skill collects team updates and writes them to a Busabase workspace. This is the core functionality of the standup board. The ingestion process is restricted to structured data and short excerpts for provenance, avoiding the storage of full chat histories. It also references environment variable names for member contacts without exposing the values to the user interface.
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted external data in the form of team chat logs (Slack, WeCom, Discord, etc.) to extract standup information. This creates an indirect prompt injection surface where malicious content in a chat log could attempt to influence the agent's parsing logic.
- Ingestion points: The
scripts/ingest_updates.mjsscript accepts payloads derived from raw chat logs and exports provided by the user. - Boundary markers: The skill instructions emphasize storing only structured items and short excerpts, rather than complete logs.
- Capability inventory: The skill can write records to Busabase and draft reminders, but it does not perform automated external communication without human review.
- Sanitization: Data is validated against defined schemas (moods, severities, etc.) and the UI implements HTML escaping for all displayed content.
Audit Metadata