Back to skill

Security audit

Subscription Cancel Call Script

Security checks for vulnerabilities and agentic risk

Overview

This is a prompt-only helper for writing honest subscription cancellation call scripts, with no code execution, network access, credential use, or persistence.

Installers should understand this skill helps draft scripts and checklists only; it does not cancel services for you. Avoid entering passwords, full payment numbers, one-time codes, or sensitive identity documents, consistent with the skill's own safety boundary.

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 (4)

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
97% confidence
Finding

The metadata specifies "Language: English," which imposes a language constraint. The file does not offer the user a language choice, opt-in, or a documented justification for restricting the skill to English only.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The statement "English/ASCII only; no non-English content" is a natural-language policy concern because it reinforces a language/locale restriction without user choice or a stated business or compliance need. This goes beyond metadata and presents the limitation as a requirement.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The manifest sets "language": "en", which imposes a specific language/locale in a user-facing skill. There is no indication elsewhere in the file that this is optional, user-selectable, or justified as a region-specific constraint.

Content

No source excerpt is available for this finding.

Vague Triggers

Low
Category
Not specified by scanner
Confidence
89% confidence
Finding

This markdown file includes a sample activation prompt, "I need to cancel my gym membership... Write me a firm call script," as the install-first input, but it does not define a bounded set of trigger phrases or exclusion conditions. Because the skill is described as providing a "clear trigger" without specifying scope or negative examples, the invocation language may overlap with ordinary conversation about cancellations.

Content

No source excerpt is available for this finding.