doppler
Pass
Audited by Gen Agent Trust Hub on Nov 21, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
- [COMMAND_EXECUTION]: The skill utilizes the Doppler CLI to execute arbitrary shell commands through the
doppler runcommand (e.g.,doppler run -- <command>), which injects secrets into the process environment. - [INDIRECT_PROMPT_INJECTION]: The skill processes external data in the form of secret values which may contain instructions targeting the agent.
- Ingestion points: Sensitive data is ingested via
doppler secrets getanddoppler secrets downloadas described inSKILL.md. - Boundary markers: There are no delimiters or warnings to ignore embedded instructions when handling the retrieved secrets.
- Capability inventory: The skill can execute shell commands (
doppler run), create/delete projects, and modify environment configurations. - Sanitization: No sanitization or validation is applied to the secret values before they are used in the agent's context or shell commands.
- [EXTERNAL_DOWNLOADS]: The
install_commanddownloads the official Doppler CLI from thedopplerhqHomebrew tap, which is a well-known service for secrets management.
Audit Metadata