lindy-install-auth
Pass
Audited by Gen Agent Trust Hub on Sep 9, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill instructs users to install official SDKs for the Lindy AI platform via public registries. Evidence:
npm install @lindy-ai/sdkandpip install lindy-sdkin references/implementation-guide.md. - [COMMAND_EXECUTION]: Bash commands are used to configure environment variables and test API connectivity using curl. Evidence:
curlPOST requests to the Lindy AI webhook endpoint andexportcommands for credential management. - [INDIRECT_PROMPT_INJECTION]: The skill creates a surface for indirect instructions by processing external webhook data. 1. Ingestion points: Webhook trigger URLs and task history described in SKILL.md. 2. Boundary markers: The instructions recommend the use of synthetic test fixtures to limit exposure. 3. Capability inventory: The skill utilizes Bash (curl), Read, Write, and Edit tools. 4. Sanitization: Absent; the skill relies on manual user verification and does not include automated sanitization logic for external data.
Audit Metadata