auth-flow-designer
Pass
Audited by Gen Agent Trust Hub on Sep 25, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes user-supplied application requirements to generate authentication architecture plans in Markdown and JSON formats.
- Ingestion points: User descriptions of application types and consumer needs in
SKILL.mdare used to fill out report templates. - Boundary markers: The skill does not define explicit delimiters or instructions to isolate user-provided data within the generated output reports.
- Capability inventory: The skill requires the ability to write files to the
docs/api-report/directory to store the generated plans. - Sanitization: No explicit sanitization or escaping mechanisms are specified for the user-provided content before it is interpolated into the output files.
Audit Metadata