printautopilot
Pass
Audited by Gen Agent Trust Hub on Mar 12, 2026
Risk Level: SAFE
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill instructs the user to install the
@membranehq/clipackage from the NPM registry and occasionally usenpxto run the latest version. This is a vendor-owned resource necessary for the skill's primary function. - [COMMAND_EXECUTION]: The skill relies on shell commands using the
membraneCLI to manage connections, discover API actions, and execute requests against the PrintAutopilot service. These commands are documented for the intended administrative and integration tasks. - [PROMPT_INJECTION]: The skill ingests data from external API responses via the
membrane action runandmembrane requestcommands, which introduces an indirect prompt injection surface. As this is the fundamental purpose of the integration and no malicious override patterns are present, this is considered a standard operational risk. - [CREDENTIALS_UNSAFE]: The skill explicitly advises against asking users for API keys or tokens, instead delegating authentication to the Membrane platform, which is a positive security practice.
Audit Metadata