chief-of-staff
Pass
Audited by Gen Agent Trust Hub on Oct 22, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill establishes an attack surface where instructions embedded in external data could influence agent behavior.
- Ingestion points: The agent is instructed in
SKILL.mdto access data sources including logs from running processes, test environment databases, and the browser. - Capability inventory: The agent is empowered in
SKILL.mdto modify the environment, create lint rules, and establish coding standards. - Boundary markers: No specific delimiters or instructions to ignore embedded commands in the processed data are provided.
- Sanitization: No sanitization or validation protocols are described for the external data being processed.
Audit Metadata