effect-atom-rpc
Pass
Audited by Gen Agent Trust Hub on May 15, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill serves as a standard technical reference for the Effect reactivity and RPC system.
- [PROMPT_INJECTION]: The skill describes patterns for ingesting data from remote RPC endpoints, which constitutes an indirect prompt injection surface.
- Ingestion points: RPC query responses ingested into the agent context via the query atom results described in SKILL.md.
- Boundary markers: No explicit prompt boundary markers are defined in the instructions to isolate remote data from agent instructions.
- Capability inventory: The agent has the capability to perform network mutations (write operations) and read local repository files in the repos/effect/ path.
- Sanitization: The skill implements robust data validation using effect/Schema to ensure ingested data matches expected types.
Audit Metadata