chief-of-staff
Pass
Audited by Gen Agent Trust Hub on Oct 8, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONPERSISTENCE
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to process data from external sources such as logs, databases, and browser screenshots.
- Ingestion points: SKILL.md specifies accessing logs, test environment databases, and web browsers.
- Boundary markers: There are no explicit delimiters or instructions to ignore embedded commands within these data sources.
- Capability inventory: The agent is empowered to modify environments, including lint rules and coding standards.
- Sanitization: No sanitization logic is defined for external data.
- [PERSISTENCE]: The skill describes the use of recurring schedules.
- Evidence: SKILL.md explicitly instructs the agent to only suggest schedules to the user and forbids the agent from creating scheduled jobs or recurring runs itself.
Audit Metadata