instantly-local-dev-loop
Pass
Audited by Gen Agent Trust Hub on Sep 11, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingests data from external API endpoints and webhooks, which could potentially contain malicious instructions meant to influence the agent's behavior.
- Ingestion points: Data enters the agent's context through API responses in
src/instantly.tsand incoming webhook request bodies insrc/webhook-server.ts. - Boundary markers: The implementation lacks explicit boundary markers or instructions to treat data from these external sources as untrusted.
- Capability inventory: The skill has access to potentially sensitive tools including
Bash(npm:*),Bash(curl:*),Write, andEdit, as defined in theSKILL.mdfrontmatter. - Sanitization: There is no evidence of data sanitization, schema validation, or content filtering for the information retrieved from external endpoints.
Audit Metadata