Pilot Alert

Security checks across static analysis, malware telemetry, and agentic risk

Overview

This instruction-only alerting skill uses expected CLI, webhook, and agent-message commands for its stated purpose, but users should configure trusted sources and destinations carefully.

Before using this skill, confirm that pilotctl and the Pilot daemon are trusted, subscribe only to the event topics you intend to monitor, verify webhook URLs and target agents, and avoid forwarding sensitive data in alert payloads.

Static analysis

No static analysis findings were reported for this release.

VirusTotal

VirusTotal findings are pending for this skill version.

View on VirusTotal

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.

#
ASI02: Tool Misuse and Exploitation
Low
What this means

If invoked with the wrong source, topic, or webhook URL, alerts could be sent to unintended recipients.

Why it was flagged

The skill permits Bash and documents pilotctl, jq, and curl pipelines. This is expected for alert subscription and webhook delivery, but shell-based workflows can perform outbound actions if misconfigured.

Skill content
allowed-tools:
  - Bash
Recommendation

Use narrow event topics, verify webhook URLs and target hostnames, and review payloads before enabling an alert workflow.

#
ASI07: Insecure Inter-Agent Communication
Low
What this means

Event details may be delivered to external services such as Slack or to an on-call agent.

Why it was flagged

The skill is designed to forward alert data to external webhooks and other agents, which is purpose-aligned but creates data-boundary considerations.

Skill content
Supports webhook delivery and direct agent messaging.
Recommendation

Only connect trusted source agents and destination services, and avoid including secrets or sensitive customer data in alert payloads.

#
ASI06: Memory and Context Poisoning
Info
What this means

A small amount of alert metadata may remain temporarily on the local machine.

Why it was flagged

The deduplication example stores alert keys and timestamps in a temporary local cache. This is proportionate for deduplication and does not show broad indexing or cross-task memory reuse.

Skill content
ALERT_FILE="/tmp/alert-cache.txt"
Recommendation

Place the cache in a controlled location if needed and clear it when alert deduplication state should not persist.