Back to skill

Security audit

Work Productivity Proactive Agent Workflow Helper

Security checks for vulnerabilities and agentic risk

Overview

The scanners rate this skill benign with high confidence: they found no reported security issues, but noted that broad everyday keywords could cause it to activate outside its intended workflow context.

The verdict is benign, but benign does not mean risk-free. Before installing, consider whether the broad activation wording could make the skill apply to unrelated requests; the scanners report no other security concerns, and their analysis covered all listed components.

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 (6)

Activation keywords include broad everyday terms without scope restrictions.

Medium
Category
Trigger Abuse
Confidence
94% confidence
Finding

The usage section lists generic keywords such as task, needs, partners, and transform, which overlap with ordinary requests unrelated to proactive-agent workflows. Although specific invocation examples follow, the file does not clarify that these generic words alone must not activate the skill or provide exclusion conditions.

Content

No source excerpt is available for this finding.

Activation keywords include everyday terms without a clear domain restriction.

Medium
Category
Trigger Abuse
Confidence
99% confidence
Finding

The trigger list includes broad terms such as task, needs, transform, followers, and partners, which commonly appear in requests unrelated to Proactive Agent workflows. Line L04 similarly describes broad invocation conditions, and no explicit exclusions or requirement for a Proactive Agent context prevents unintended activation.

Content

No source excerpt is available for this finding.

Generic keywords can activate this skill for unrelated requests.

Medium
Category
Trigger Abuse
Confidence
99% confidence
Finding

The trigger list includes everyday terms such as task, needs, partners, and transform, without requiring a connection to Proactive Agent workflows. Line L04 also explicitly treats generic terms as activation conditions, so unrelated requests can invoke this skill despite its specialized purpose.

Content

No source excerpt is available for this finding.

Implicit invocation is enabled despite an ambiguous, truncated skill description that does not define when the skill should activate.

Medium
Category
Trigger Abuse
Confidence
96% confidence
Finding

The description discusses demand for proactive workflows rather than defining a specific task or activation condition, and the default prompt ends mid-word after broadly mentioning bug fixing. With implicit invocation enabled, this provides no clear boundary between this skill and unrelated productivity or debugging requests.

Content

No source excerpt is available for this finding.

Activation keywords include broad everyday terms without scope constraints.

Low
Category
Trigger Abuse
Confidence
96% confidence
Finding

The Usage section lists generic keywords such as task, transform, partners, and needs without requiring a Proactive Agent or Clawhub context. These terms overlap with ordinary requests and unrelated workflows, creating ambiguous activation conditions despite the more specific trigger sentences below.

Content

No source excerpt is available for this finding.

Usage keywords include broad everyday terms without activation constraints.

Low
Category
Trigger Abuse
Confidence
93% confidence
Finding

The usage signals include generic keywords such as "task", "needs", "partners", and "transform", which overlap with requests unrelated to Proactive Agent workflows. Although specific trigger sentences are also listed, the file does not require a domain-specific match or exclude unrelated uses of these keywords.

Content

No source excerpt is available for this finding.