engineering-design-thinking
Pass
Audited by Gen Agent Trust Hub on Sep 16, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill workflow requires the agent to ingest and analyze external data (Gate 2: 'Inspect relevant code, data flow, dependencies...'), which constitutes a surface for indirect prompt injection.
- Ingestion points: The agent reads existing code, dependencies, and deployment constraints from the filesystem. The WebFetch and WebSearch tools allow the ingestion of data from external websites and APIs.
- Boundary markers: There are no specific instructions or delimiters provided to ensure that instructions found within analyzed code comments or web content are ignored.
- Capability inventory: The agent has access to Edit, Write, and restricted Bash (git) tools, which allow it to modify the codebase based on potentially poisoned input.
- Sanitization: The skill lacks explicit sanitization or verification steps for data retrieved from the codebase or external network sources.
Audit Metadata