instantly-prod-checklist
Pass
Audited by Gen Agent Trust Hub on Sep 11, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill fetches dynamic content from the Instantly.ai API and presents it directly to the agent's context for evaluation and reporting. If an external source (e.g., a campaign name, webhook URL, or lead data) is populated with malicious instructions, the agent could potentially be influenced by that content during the checklist execution.
- Ingestion points: Data is ingested through multiple
instantly()API calls inSKILL.md, including/accounts,/accounts/test/vitals,/campaigns/${campaignId},/campaigns/analytics, and/webhooks. - Boundary markers: None. The API responses are processed and logged to the console without delimiters or instructions to ignore embedded commands.
- Capability inventory: The skill has access to
Read,Write,Edit,Bash(for curl and npm), andGreptools. - Sanitization: None. The skill interpolates and prints raw strings from the API responses directly into the terminal output.
Audit Metadata