ByteRover - Headless
Analysis
This is a coherent ByteRover CLI guide, but it uses a ByteRover API key and can persist or sync selected project context to cloud, so users should approve what is shared.
Findings (4)
Artifact-based informational review of SKILL.md, metadata, install specs, static scan signals, and capability signals. ClawScan does not execute the skill or run runtime probes.
Checks for instructions or behavior that redirect the agent, misuse tools, execute unexpected code, cascade across systems, exploit user trust, or continue outside the intended task.
For pull and push operations, you should ask for user permission first ... For push operations, always use `-y` to skip confirmation in headless mode.
Push and pull can mutate or sync the context tree. The instructions include a user-permission step, but the actual headless push command bypasses the CLI confirmation prompt.
"requires":{"bins":["brv"]},"install":[{"id":"npm","kind":"node","package":"@byterover/cli","bins":["brv"]The skill depends on an external ByteRover CLI package rather than included code. This is normal for a CLI wrapper, but the reviewed artifacts do not contain the package implementation.
Checks whether tool use, credentials, dependencies, identity, account access, or inter-agent boundaries are broader than the stated purpose.
ask them to provide: 1. **API key** - for authentication ... brv login --api-key <key>
The skill instructs use of a ByteRover API key for login. This is expected for the service, but it grants account access and is not declared as a primary credential in the registry metadata.
Checks for exposed credentials, poisoned memory or context, unclear communication boundaries, or sensitive data that could leave the user's control.
ByteRover maintains a context tree that stores patterns, decisions, and implementation details about a project ... brv curate ... --files src/middleware/auth.ts ... brv push ... ByteRover cloud storage
The skill stores project knowledge, can include selected file content, and can sync the context tree to cloud storage. This is aligned with the stated purpose but can persist sensitive project details.
