api-client-generator
Pass
Audited by Gen Agent Trust Hub on Aug 27, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to process and act upon user-provided API integration requirements, third-party API patterns, and SDK generation requests, which introduces a potential attack surface.
- Ingestion points: Untrusted data enters the context via user requests describing third-party APIs, webhooks, and integration patterns (SKILL.md).
- Boundary markers: The instructions lack explicit delimiters or instructions to treat data within API specifications as untrusted, which could lead the agent to follow instructions embedded within a malicious API definition.
- Capability inventory: The skill allows the agent to use
Bash(cmd:*),Write, andEdittools, meaning an injection could lead to arbitrary command execution or file system changes (SKILL.md). - Sanitization: There are no defined mechanisms for sanitizing or validating external API content before it is processed by the agent's code generation or execution tools.
Audit Metadata