using-aisdlc
Pass
Audited by Gen Agent Trust Hub on Mar 10, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill exhibits an indirect prompt injection attack surface because it processes untrusted requirement data from external files to guide subsequent implementation steps.\n
- Ingestion points: Processes files such as
requirements/raw.mdandrequirements/solution.mdas defined in the routing rules.\n - Boundary markers: No explicit delimiters or instructions to ignore embedded commands are specified for the requirement content.\n
- Capability inventory: The router coordinates transitions to worker skills like
spec-executewhich perform code generation and file system modifications.\n - Sanitization: No explicit sanitization of requirement text is performed before it is used to drive the SDLC process.\n- [SAFE]: No hardcoded credentials, sensitive file path access, or unauthorized network operations were detected.\n- [SAFE]: No obfuscation or multi-layer encoding techniques were found in the routing logic or metadata.
Audit Metadata