creating-case-studies
Pass
Audited by Gen Agent Trust Hub on Sep 22, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted user-provided information to generate structured case studies, presenting a potential surface for indirect prompt injection.
- Ingestion points: Data enters the context through user responses to the questions in 'Step 1: Gather Case Study Inputs' in SKILL.md.
- Boundary markers: The instructions do not define explicit delimiters or 'ignore embedded instructions' warnings to isolate user data from the agent's logic during the generation process.
- Capability inventory: The skill has no capabilities to execute commands, write to the file system, or perform network operations. Its scope is limited to text generation.
- Sanitization: There are no instructions for sanitizing or validating the input data before it is interpolated into the case study templates.
Audit Metadata