Back to skill

Security audit

ParrotNotes

Security checks for vulnerabilities and agentic risk

Overview

The skill is a coherent ParrotNotes connector, but its broad auto-invocation can access sensitive meeting notes even when the user may not have explicitly meant ParrotNotes.

Install only if you are comfortable letting the agent access ParrotNotes meeting content through the MCP connector. Be especially careful with ambiguous requests about meetings or transcripts, and confirm before saving or overwriting insights in ParrotNotes.

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)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The trigger description is broad enough to activate on generic requests about meetings, notes, transcripts, action items, translation, or repurposing content, even when the user did not explicitly mean ParrotNotes. This can cause unintended tool use against a connected external data source, creating privacy and authorization risk through over-collection or retrieval of sensitive meeting content.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

The skill enables implicit invocation without any visible trigger constraints or narrowing conditions, which can cause the agent to auto-select this connector whenever a user mentions meetings, notes, transcripts, or similar terms. Because the connected MCP tool can access and summarize potentially sensitive meeting notes, broad auto-invocation increases the chance of unintended data access, disclosure, or actions on the user's ParrotNotes content.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.