add-your-agent
Pass
Audited by Gen Agent Trust Hub on Oct 19, 2026
Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill requires the execution of shell commands using
docker,curl, andjq. These tools are used to build and push container images to registries (such asghcr.io), manage registry authentication, and perform administrative operations on the Veris Bench API. - [EXTERNAL_DOWNLOADS]: The skill interacts with external services, specifically
bench.api.veris.aifor platform orchestration and various container registries for image distribution. These network operations are necessary for the skill's primary function of agent registration and benchmarking. - [INDIRECT_PROMPT_INJECTION]: The skill integrates an agent that will process untrusted data from bench trials, including agent transcripts, container logs, and API responses. While this presents a potential injection surface, the risk is inherent to the benchmarking process and is managed through the use of structured data formats like JSON.
Audit Metadata