Back to skill

Security audit

Whisper AI Audio to Text Transcriber

Security checks for vulnerabilities and agentic risk

Overview

This skill only gives instructions for summarizing user-provided transcripts and does not request tools, persistence, credentials, or hidden access.

Before using this skill, review transcripts for private, regulated, or confidential details and redact anything unnecessary; the skill is otherwise a straightforward formatting and summarization aid.

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 (2)

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

This skill encourages users to submit transcripts, which commonly contain sensitive personal, business, financial, health, or confidential meeting information, yet it provides no privacy warning or handling guidance. That omission can lead to accidental disclosure of sensitive content to the system or to downstream summaries that expose private details more broadly.

Content

No source excerpt is available for this finding.

Vague Triggers

Low
Category
Not specified by scanner
Confidence
80% confidence
Finding

The 'When to Use' section lists generic intents such as 'summarize a transcript' and 'generate meeting notes' but does not define exclusions, constraints, or negative examples. In a markdown skill description, this can make invocation scope ambiguous because it does not clarify when similar everyday requests should not trigger this skill.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.