backend-dev
Pass
Audited by Gen Agent Trust Hub on Oct 4, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill's workflow involves ingesting external architecture designs and API contracts, which creates a potential surface for indirect prompt injection.
- Ingestion points: Phase 1 and Phase 2 workflows in SKILL.md describe the ingestion of architecture designs, API contracts, and component specifications.
- Boundary markers: The instructions do not define specific delimiters or instructions to ignore embedded commands within these external documents.
- Capability inventory: The skill has access to the
Bashtool and is responsible for writing and executing code and tests. - Sanitization: No sanitization or filtering logic is prescribed for the architectural inputs before the agent processes them, although the skill correctly instructs the agent to implement sanitization for the final software products.
Audit Metadata