amazon-cognito
Pass
Audited by Gen Agent Trust Hub on Apr 22, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill installs the
@membranehq/clipackage globally using npm. This is a vendor-owned tool required for the skill's primary functionality. - [COMMAND_EXECUTION]: Utilizes the
membranecommand-line tool to perform operations such as searching for connectors, establishing connections, and executing API actions. - [PROMPT_INJECTION]: The skill retrieves and processes external data which constitutes an indirect prompt injection surface.
- Ingestion points: Tool outputs from
membrane action listandmembrane connection list(referenced in SKILL.md). - Boundary markers: None identified.
- Capability inventory: Includes the ability to run shell commands and make network requests via
membrane action runandmembrane request. - Sanitization: No explicit sanitization of tool output is defined within the skill instructions.
Audit Metadata