albato
Pass
Audited by Gen Agent Trust Hub on Mar 4, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill requires the installation of the
@membranehq/clipackage from NPM. This is a vendor-provided tool from Membrane used for platform communication. - [COMMAND_EXECUTION]: The skill uses shell commands via the
membraneCLI to search for connectors, manage authentication, and run actions on the Albato platform. - [PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface because it ingests and processes data from external sources. 1. Ingestion points: Data is retrieved into the agent context via
membrane action listandmembrane requestcommands. 2. Boundary markers: No explicit delimiters or safety instructions are provided to the agent to distinguish external content from system instructions. 3. Capability inventory: The skill can execute shell commands through the CLI and perform authenticated network requests. 4. Sanitization: No explicit output sanitization or schema validation is implemented for the ingested data.
Audit Metadata