Back to skill

Security audit

FTPilot

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed cycling-coach integration that reads Intervals.icu training data and can create workout events, with no evidence of hidden or unrelated behavior.

Install this only if you intend to let the skill use your Intervals.icu athlete data for coaching. Before allowing it to create calendar events, confirm the planned workout details yourself, especially because some trigger phrases may match ordinary cycling questions.

Vulnerability Patterns
  • Skill Instruction HijackingAlters the agent's session goals or safety constraints when the skill loads
  • Agent Memory PoisoningWrites attacker-controlled rules into memory that affect later sessions
  • Remote Payload Retrieval and ExecutionFetches external code whose behavior can change after review
  • Embedded Malicious CodeShips malicious scripts inside the skill and executes them locally
  • Unauthorized Access and Privilege EscalationObtains permissions beyond the task's legitimate needs
Vulnerability Patterns
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (1)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
90% confidence
Finding

The trigger phrases are broad enough to match ordinary cycling discussion such as 'my FTP' or 'training plan', which can cause the skill to activate outside a clearly intended consent boundary. In a skill that can access athlete data and create training events, ambiguous activation increases the chance of unintended tool use, privacy exposure, or calendar modification based on casual conversation.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.