ClawHub
Back to skill

Security audit

Product Validation Planner

Security checks for vulnerabilities and agentic risk

Overview

This is a text-only planning skill with no executable code, but its automatic activation wording is broader than its product-validation purpose needs.

Before installing, understand that this skill may be selected for broad product or help-related prompts because implicit invocation is enabled and the trigger words are generic. It appears safe from a code-execution or data-access standpoint, but the publisher should narrow activation language to reduce accidental use.

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
  • 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 (5)

Vague Triggers

High
Category
Not specified by scanner
Confidence
93% confidence
Finding

The manifest description defines activation using vague conditions like 'creative-and-content, ask-hn, ask, product, very' and broad needs such as any request for a workflow, checklist, analysis, or implementation support. Because these boundaries are not specific, the orchestrator may route many unrelated conversations into this skill, increasing the chance of misfires and reducing the reliability and safety of skill selection.

Content

No source excerpt is available for this finding.

Vague Triggers

High
Category
Not specified by scanner
Confidence
98% confidence
Finding

The trigger list is overly broad and includes generic terms such as 'ask', 'product', 'very', 'high', 'quality', and 'ready', which are common in ordinary user prompts. This can cause accidental invocation in unrelated contexts, leading to prompt-routing errors, unintended access to the skill's instructions, or interference with more appropriate skills.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
96% confidence
Finding

The skill description and default prompt are vague and broadly framed ('Help for a Product'), which can cause the agent to invoke this skill for loosely related requests. Overbroad routing increases the chance of unintended activation, prompt-context leakage into an unrelated workflow, and unsafe delegation decisions because the agent lacks clear task boundaries.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

Enabling implicit invocation without meaningful trigger constraints allows the platform to auto-select this skill based on weak semantic matches. In combination with the broad product/help wording, this raises the likelihood of misrouting user requests to the skill, which can produce irrelevant actions, expose context unnecessarily, or bypass safer specialized skills.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
96% confidence
Finding

The trigger set includes broad, everyday terms such as "ask," "product," "very," "high," "quality," and "ready," which can match many unrelated user requests and cause the skill to activate unintentionally. In an agent routing context, this can misroute conversations, override more appropriate skills, and lead to irrelevant or lower-quality outputs even without explicit malicious content.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.