instantly-multi-env-setup
Pass
Audited by Gen Agent Trust Hub on Sep 11, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill incorporates an attack surface by combining external data retrieval with filesystem modification capabilities. Instructions embedded in external documentation or package metadata could theoretically influence the agent's actions.
- Ingestion points: As documented in
SKILL.mdandreferences/official-docs.md, theWebFetchtool is intended to read content fromdeveloper.instantly.ai,api.instantly.ai, and the npm registry. - Boundary markers: The instructions do not define specific delimiters or "ignore embedded instructions" headers when handling data fetched from these external URLs.
- Capability inventory: The skill is configured with
WriteandEdittools inSKILL.md, providing the agent with the ability to alter local project files based on the untrusted external content. - Sanitization: While the skill includes instructions for redacting sensitive fields and validating workspace IDs, it lacks explicit sanitization or filtering logic for text content interpolated into the agent's context from external sources.
Audit Metadata