agency-circles-for-systems-action
Pass
Audited by Gen Agent Trust Hub on Sep 16, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONNO_CODE
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted user data through multiple input fields and interpolates them directly into the prompt template.
- Ingestion points: The fields
system_issue_or_aspiration,context,iceberg_or_system_map,student_level,stakeholders, andconstraintsinSKILL.mdserve as entry points for untrusted data. - Boundary markers: Absent; the prompt does not use delimiters or explicit instructions to ignore embedded commands within the user-provided context.
- Capability inventory: The skill has no access to external tools, network requests, or file system operations, which significantly mitigates the risk of this attack surface.
- Sanitization: No input validation or sanitization mechanisms are implemented for the provided data.
- [NO_CODE]: This skill consists entirely of markdown documentation and a structured prompt template. It does not include any executable scripts, binary files, or external software dependencies.
Audit Metadata