Back to skill

Security audit

call-pro

Security checks for vulnerabilities and agentic risk

Overview

This call-management skill stores and reads sensitive call notes locally, but the reviewed artifacts disclose that purpose and do not show hidden sharing, network access, persistence, or destructive behavior.

Install only if you are comfortable keeping call notes, contact context, commitments, and follow-ups in local memory/calls files. Be careful using it for confidential conversations, and periodically review or delete stored call records you no longer need. Expect some advertised workflows to require missing scripts or future implementation.

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
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (2)

Undeclared Tool Scope

Medium
Category
MCP Least Privilege
Confidence
84% confidence
Finding

The skill advertises local storage access and references reading conversation history and related records, but it does not declare any explicit tool scope such as permissions or allowed-tools. That mismatch increases the risk of unintended file access or over-privileged execution because the platform cannot clearly constrain what filesystem operations the skill is expected to perform.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
96% confidence
Finding

The activation language is very broad: it triggers on generic mentions of phone calls, meetings, conversations, commitments, or follow-ups. In practice, that can cause the skill to activate for ordinary chat and route sensitive conversational content into local memory files, increasing privacy risk and the chance of inappropriate data capture.

Content

No source excerpt is available for this finding.