Mcporter Railway Query
Analysis
This appears to be a read-only train ticket query helper, with the main caveat that it depends on a trusted local mcporter/MCP setup.
Findings (3)
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.
mcporter call 12306.get-tickets \ date="$DATE" \ fromStation="$FROM_STATION" \ toStation="$TO_STATION" \ sortFlag="startTime" \ format="text" \ --config "$CONFIG_FILE"
The helper script runs a local CLI tool using user-provided query parameters and a config path. This is central to the skill's purpose and the arguments are quoted, but it is still local tool execution.
### mcporter not found ```bash npm install -g mcporter ```
The skill requires an external globally installed CLI, but the artifacts do not pin a version or provide an install spec for that dependency. This is purpose-aligned, but users must trust the installed package.
Checks for exposed credentials, poisoned memory or context, unclear communication boundaries, or sensitive data that could leave the user's control.
"type": "sse", "url": "http://127.0.0.1:8080/sse"
The documented setup communicates with a local MCP/SSE server. This is disclosed and expected, but it creates a trust boundary between the skill, mcporter, and the local MCP server.
