create-case
Pass
Audited by Gen Agent Trust Hub on Oct 22, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingests user-provided request data and references local documentation to generate case workflows, which constitutes an ingestion surface for untrusted data. This attack surface is inherent to the skill's primary function.
- Ingestion points: User requests and the reference file
skills/paperclip/references/cases.md. - Boundary markers: No explicit delimiters or instruction bypass warnings are defined in the prompt.
- Capability inventory: The skill uses the
create_casetool and documented REST API calls. - Sanitization: No specific input sanitization or validation steps are provided in the instructions.
Audit Metadata