jpm-merchant-integrations
Pass
Audited by Gen Agent Trust Hub on Oct 14, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill collects a free-text project description from the user to tailor the generated implementation and code comments, creating a potential surface for indirect prompt injection.
- Ingestion points: User input requested in Step 2 of
SKILL.md("Briefly describe what you're building or migrating"). - Boundary markers: The instructions do not specify the use of delimiters or explicit instructions for the model to ignore embedded commands within this input.
- Capability inventory: The skill uses the input to generate code, file structures, and comments, which involves file-system operations (writing code files).
- Sanitization: No explicit sanitization, validation, or filtering of the user-provided description is described before it is interpolated into the generation prompt.
Audit Metadata