Back to skill

Security audit

Clickup Task

Security checks for vulnerabilities and agentic risk

Overview

This ClickUp task skill has a coherent purpose, but its agent instructions create a real command-injection risk when task text is passed through a shell command string.

Review before installing. The ClickUp integration itself is understandable, but the skill should be changed to call the script with structured arguments and shell interpretation disabled, enforce the visionplay/inbox allowlist, redact sensitive error output, and clearly warn users that task content is sent to ClickUp.

Vulnerability Patterns
  • Insecure Skill Coding PracticesFinds exploitable flaws such as hardcoded secrets or command injection
  • 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
Findings (1)

T09 · Insecure Skill Coding Practices

Error
Location
SKILL.md:27
Finding

Shell Command Injection Through Unsanitized Task Arguments

Content
View full analysis
" "" "<description>"' ``` ### Technical Analysis The Skill instructs the agent to interpolate the user-controlled `list`, `title`, and `description` values directly into a command string executed through `bash -lc`. Double quotes around the interpolated values do not make this construction safe. A value containing a double quote can terminate its intended argument and introduce shell control operators, command substitutions, redirections, or additional commands. The inner Bash process will parse those injected characters as shell syntax. The instruction to parse the arguments “exactly” provides no allowlist validation, escaping, or structured argument passing. Although the documentation says that `list` must be `visionplay` or `inbox`, the execution instructions do not enforce this constraint. The title and description are necessarily user-controlled free-form values. For example, a crafted title with the conceptual structure: ```text "; <attacker-command>; # ``` could produce an effective inner shell command resembling: ```sh /usr/local/bin/clickup_create_task.sh "visionplay" ""; <attacker-command>; # " "description" ``` The injected command would then be interpreted by Bash rather than passed as task-title data. The `skill.json` file also references the external script, but its implementation is not included in the audited project. Consequently, any additional validation performed by that script cannot be confirmed. Validation inside the script would not reliably mitigate commands already interpreted by `bash -lc`. ### Attack Path 1. An attacker invokes the user-accessible `/clickup-task` command ...[truncated 1322 chars]
Remediation
View remediation
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (1)

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

The skill collects user-supplied task title and description and sends them to the ClickUp API, but the markdown shown to users does not warn that this content leaves the local agent environment and is transmitted to a third-party service. This can cause unintentional disclosure of sensitive or regulated information because users may treat the command like an internal note-taking action rather than an external API submission.

Content

No source excerpt is available for this finding.