pilot-protocol
Fail
Audited by Snyk on Aug 25, 2026
Risk Level: CRITICAL
Full Analysis
CRITICAL E005: Suspicious download URL detected in skill instructions.
- Suspicious download URL detected (high risk: 0.90). The skill instructs fetching and running a direct install.sh from pilotprotocol.network — a non-vendor domain delivering a shell installer is a high-risk vector for malware distribution.
CRITICAL E006: Malicious code pattern detected in skill scripts.
- Malicious code pattern detected (high risk: 0.90). This skill enables installing a persistent P2P daemon that auto-accepts public service messages and installs remote app-store packages, creating clear vectors for remote code execution, supply-chain compromise, and data exfiltration if abused.
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (medium risk: 0.30). The “pilot-protocol” workflow can ingest outsider-authored free text because it reads JSON replies written to
~/.pilot/inbox/*.jsonfrompilotctl send-message list-agents ... --wait, where the returned agent/service payload may contain attacker-controlled text.
MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).
- Potentially malicious external URL detected (high risk: 0.90). The skill instructs downloading and then executing an installer fetched at runtime from https://pilotprotocol.network/install.sh (curl ... -o "$installer" then sh "$installer"), which fetches remote code and runs it.
MEDIUM W013: Attempt to modify system services in skill instructions.
- Attempt to modify system services in skill instructions detected (high risk: 1.00). The skill explicitly instructs downloading and executing an installer (sh "$installer"), starting a persistent daemon that joins a public P2P network, and installing local app-store packages — all state-changing actions that modify the host environment and can alter system state.
Issues (5)
E005
CRITICALSuspicious download URL detected in skill instructions.
E006
CRITICALMalicious code pattern detected in skill scripts.
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
W012
MEDIUMUnverifiable external dependency detected (runtime URL that controls agent).
W013
MEDIUMAttempt to modify system services in skill instructions.
Audit Metadata