client-generation
Pass
Audited by Gen Agent Trust Hub on Oct 9, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONNO_CODE
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill instructions define a workflow for processing external API contracts to generate executable code, creating a surface for indirect prompt injection. \n
- Ingestion points: The skill takes 'Canonical API contract source' as input (SKILL.md). \n
- Boundary markers: Absent; no instructions are provided to delimit the contract data or ignore embedded instructions. \n
- Capability inventory: The skill is authorized to write 'Generated client code', update import paths, and commit regenerated artifacts (SKILL.md). \n
- Sanitization: Absent; no validation or escaping of the input contract content is specified by the instructions.\n- [NO_CODE]: The skill consists only of documentation and instructions; no executable scripts or source code are provided within the skill package.
Audit Metadata