api-contract
Pass
Audited by Gen Agent Trust Hub on Aug 30, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingests feature requirements from external
specs.mdfiles to generateapi-contract.md. This represents an indirect prompt injection surface as malicious instructions in the specifications could influence the agent's behavior or be propagated to downstream backend and frontend agents via the generated contract.\n - Ingestion points: The agent is instructed to read
.claude/sprint/[N]/specs.mdto define feature scope.\n - Boundary markers: The instructions do not define delimiters or explicit "ignore" warnings to prevent the agent from obeying instructions embedded within the specification files.\n
- Capability inventory: The skill utilizes the Read tool and generates documentation that coordinates the implementation work of multiple agents through SPAWN REQUEST blocks.\n
- Sanitization: No validation, filtering, or sanitization of the input specification content is specified before it is processed.
Audit Metadata