ClawHub
Back to skill

Security audit

Add Flashcard 4c0314

Security checks for vulnerabilities and agentic risk

Overview

This is a simple markdown-only learning note for a geography flashcard app lesson, with no executable code or high-impact permissions.

Installation appears low risk. The main caveat is that the skill may activate on unrelated mentions of "53" or broad geography/build terms, so users may want the publisher to narrow the trigger wording before relying on it in busy workflows.

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 (2)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
97% confidence
Finding

The trigger conditions are broad and ambiguous, including a generic numeric trigger ("53") and a loose condition for users needing related help. This can cause unintended activation in unrelated conversations, leading the agent to apply the wrong skill or inject irrelevant behavior into user workflows.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
96% confidence
Finding

The duplicated trigger block repeats the same vague activation pattern, again including an overly generic token and broad related-help language. Repetition increases the chance of accidental invocation and makes matching behavior harder to reason about, which can amplify misfires across normal user interactions.

Content

No source excerpt is available for this finding.