internal-controls-design
Pass
Audited by Gen Agent Trust Hub on Sep 24, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONNO_CODE
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to process external, potentially untrusted data regarding an organization's internal controls and financial reporting environment.
- Ingestion points: External data enters the context through the 'Required Inputs' section, including organizational profiles, scope definitions, and 'Known Issues'.
- Boundary markers: The skill lacks explicit delimiters or instructions for the agent to ignore potential commands embedded within the user-supplied input data.
- Capability inventory: While the skill itself does not include executable code, it leverages the agent's capabilities to generate complex financial reports and remediation plans, which could be manipulated by adversarial input.
- Sanitization: There are no defined procedures for validating, filtering, or sanitizing the content provided in the input fields before it is used to generate the final COSO-aligned output.
Audit Metadata