instantly-sdk-patterns
Pass
Audited by Gen Agent Trust Hub on Sep 11, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from local repositories and external documentation sources.\n
- Ingestion points: Source code analysis via
Read,Glob, andGreptools; documentation and metadata retrieval viaWebFetchas specified inSKILL.md.\n - Boundary markers: While formal prompt delimiters are absent, the skill provides strict directives to redact response bodies and authorization headers.\n
- Capability inventory: File modification via
WriteandEdit; network retrieval viaWebFetch.\n - Sanitization: Explicit instructions are included to redact sensitive fields and credentials before outputting data to the agent context.\n- [SAFE]: No malicious code, obfuscation, or unauthorized data exfiltration patterns were detected. The skill enforces security best practices for handling API v2 keys, including using server-side secret managers and preventing credential exposure in logs or URLs.
Audit Metadata