platform-exception
Pass
Audited by Gen Agent Trust Hub on Sep 2, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill establishes an attack surface for indirect prompt injection by processing external data into exception messages and error responses.
- Ingestion points: Untrusted data enters the context via controller parameters and Bean Validation attributes (@NotBlank, @Email) as described in SKILL.md.
- Boundary markers: No specific delimiters are specified for the interpolation of user-provided data into the error message fields.
- Capability inventory: The skill defines logic for generating structured JSON error responses; it does not utilize high-risk tools for file system writing, network operations, or arbitrary code execution.
- Sanitization: The skill contains explicit defensive instructions in the 'Implementation Guidance' section to omit secrets, PAN, CVV, PIN, OTP, and credentials from context data, and it includes configuration for masking sensitive fields in references/configuration.md.
- [EXTERNAL_DOWNLOADS]: The skill references the Maven dependency 'com.bankfab.ksa.middleware:platform-exception'. This is a project-specific artifact necessary for the core functionality of the skill as a standardized middleware utility.
Audit Metadata