Back to skill

Security audit

cold-email-writer

Security checks for vulnerabilities and agentic risk

Overview

The skill leaves sending under your control, but its advertised compliance checker misses obvious problems and can give false reassurance.

Treat this as a drafting aid, not a reliable compliance check. Independently review sender details, subjects, postal addresses, opt-out functionality, and claims before sending. The optional Windows program is unnecessary for the local workflow and needs separate review.

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
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • 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 (3)

Description-Behavior Mismatch

High
Category
MCP Tool Poisoning
Confidence
99% confidence
Finding

The static report describes ineffective compliance checks that could allow missing addresses, missing opt-out mechanisms, and misleading content to escape detection while users rely on the advertised compliance workflow. This is a meaningful validation-integrity weakness in a compliance-focused skill, although manual sending limits direct impact and failure to generate drafts is not itself a vulnerability. The script was not supplied, so the reported implementation defects cannot be independently verified from SKILL.md.

Content

No source excerpt is available for this finding.

Skill declares no tool scope ('permissions' or 'allowed-tools') but code capabilities were detected: file_write.

Medium
Category
MCP Least Privilege
Confidence
70% confidence
Finding

Without declared permissions the skill's intent is opaque and cannot be validated.

Content

No source excerpt is available for this finding.

The compliance report does not check for missing required email elements despite the manifest's claim.

Medium
Category
Excessive Agency
Confidence
99% confidence
Finding

The linter only searches for matches and never flags the absence of required elements such as a postal address or opt-out mechanism, so incomplete emails can receive a 'No flags' report. It also treats regular-expression patterns as literal substrings, causing ordinary risky wording to go undetected. Because compliance checking is a core advertised function, these false negatives can mislead representatives into sending noncompliant outreach, although the script does not send email itself.

Content

No source excerpt is available for this finding.