Pilot Task Router
Security checks across static analysis, malware telemetry, and agentic risk
Overview
This instruction-only skill is coherent for routing Pilot Protocol tasks, but users should remember it can send task details to discovered external agents.
This skill appears benign and purpose-aligned. Before installing, make sure you trust your Pilot Protocol setup and avoid routing tasks that contain secrets, private data, or irreversible instructions unless you have verified the destination agent.
Static analysis
No static analysis findings were reported for this release.
VirusTotal
VirusTotal findings are pending for this skill version.
Risk analysis
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.
Task details may be sent to another agent selected from discoverable peers.
The skill submits task text to a selected Pilot peer, which is expected for a task router but involves inter-agent data sharing.
pilotctl --json task submit "$BEST_AGENT" --task "Run ML inference"
Avoid including secrets or sensitive data in routed tasks unless you trust the selected Pilot agent and network.
If invoked with an inappropriate task, the agent could submit work to a peer you did not intend.
The skill exposes Bash-based pilotctl workflows for peer search and task submission; this is central to the stated purpose but gives the agent operational command capability.
allowed-tools: - Bash
Use it for explicit routing tasks and review the destination agent and task content for sensitive or high-impact work.
Setup may fail or behave unexpectedly if jq or the Pilot daemon is not installed and understood.
The SKILL.md dependency list includes jq and the Pilot protocol/daemon, while registry requirements only declare pilotctl.
Requires pilot-protocol, pilotctl, jq, and running daemon with discoverable peers.
Confirm pilotctl, jq, and the Pilot daemon are installed from trusted sources before using the skill.