Security audit

Trello Orchestrator Runner

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed Trello workflow automation guide that modifies Trello cards as its core purpose, with no hidden code or persistence found.

Install only if you want an agent to update a Trello board on your behalf. Use Trello credentials limited to the intended workspace or board, review trello-workflow-map.json before running, and avoid placing sensitive task details in cards unless they are appropriate for Trello.

A.I.G

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

SkillSpector

Vulnerability Patterns

Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code

Findings (2)

Vague Triggers

Medium

Confidence: 92% confidence
Finding: The invocation description is broad enough to match common user requests about running tasks automatically, which can cause this skill to activate in situations the user did not specifically intend. Because the skill performs state-changing Trello operations and drives a closed-loop workflow, accidental invocation could trigger unauthorized board updates, task execution, or external data handling.

Missing User Warnings

Medium

Confidence: 95% confidence
Finding: The skill explicitly requires Trello credentials and defines API calls that create cards, move cards, add comments, and update descriptions, but it provides no user-facing disclosure that data will be sent to Trello or that the board will be modified. In context, this is more dangerous because the skill is designed for automated, repeated workflow transitions, so a user may unintentionally expose sensitive task data externally or cause persistent changes across a production board.

Static analysis

No suspicious patterns detected.