aws-s3

Pass

Audited by Gen Agent Trust Hub on Mar 4, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill directs the agent to execute shell commands using the membrane CLI to manage AWS connections and perform storage operations.
  • [EXTERNAL_DOWNLOADS]: Recommends installing the @membranehq/cli global package from NPM. This is a recognized vendor resource from membranedev used for platform integration.
  • [PROMPT_INJECTION]: The skill contains an attack surface for indirect prompt injection (Category 8) due to its interaction with external storage.
  • Ingestion points: The agent retrieves data from S3 objects using the membrane action run and membrane request commands (file: SKILL.md).
  • Boundary markers: No explicit delimiters or instructions are provided to the agent to distinguish between data and potential instructions within S3 objects.
  • Capability inventory: The skill allows listing connections, running actions, and making direct API requests, which could be exploited if an ingested object contains malicious instructions.
  • Sanitization: There is no evidence of sanitization or content validation for data retrieved from S3.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 4, 2026, 08:56 AM