eigen-da
Pass
Audited by Gen Agent Trust Hub on Feb 20, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS] (LOW): The skill documentation in SKILL.md instructs users to run a Docker image from ghcr.io/layr-labs/eigenda-proxy, which is an external binary dependency.
- [PROMPT_INJECTION] (LOW): The skill is susceptible to indirect prompt injection. * Ingestion points: The retrieve method in scripts/da-api.js fetches external data from the EigenDA network. * Boundary markers: Absent; no delimiters are used to wrap or isolate retrieved content. * Capability inventory: Network operations via the axios library to local and remote endpoints. * Sanitization: Absent; data is parsed as JSON and returned directly to the agent context.
Audit Metadata