Security audit

Subscription Manager Pro

Security checks for vulnerabilities and agentic risk

Overview

This is a coherent local subscription tracker, but its cancellation wording may mislead users into thinking real paid subscriptions are cancelled when only local records are changed.

Install only if you understand this manages a local tracker, not your actual accounts. Treat 'cancel' as 'mark cancelled/remove from my records' and separately cancel with the provider. Be careful opening CSV exports in spreadsheets if subscription names, notes, or URLs came from untrusted text.

A.I.G

Vulnerability Patterns

Insecure Skill Coding PracticesFinds exploitable flaws such as hardcoded secrets or command injection
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

Findings (1)

T09 · Insecure Skill Coding Practices

Warning

Location: scripts/manager.py:359
Finding: CSV Formula Injection Through Unescaped Subscription Fields
Content: View full analysis
Remediation: View remediation

SkillSpector

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 (5)

Missing User Warnings

Medium

Category: Not specified by scanner
Confidence: 96% confidence
Finding: The README presents commands and natural-language examples like 'Cancel my Hulu subscription' and 'python scripts/manager.py remove --name "Netflix"' without clearly stating that these actions only remove the local tracking entry and do not cancel the real subscription with the provider. In a financial-management skill, this can mislead users into believing a paid service has been terminated, causing continued billing, missed renewals, and financial loss.
Content: No source excerpt is available for this finding.

Undeclared Tool Scope

Medium

Category: MCP Least Privilege
Confidence: 93% confidence
Finding: The skill advertises file-backed functionality and explicitly references local JSON storage plus a required script, but it declares no tool scope or allowed-tools constraints. In an agent environment, that means the skill can end up with broader file read/write capability than users or reviewers expect, increasing the chance of unintended modification or exposure of local data.
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 95% confidence
Finding: The invocation triggers are broad enough to activate on general budgeting, service-cost, or cancellation conversations, not just clear subscription-management requests. Over-broad auto-invocation can cause the agent to read or write subscription data in contexts where the user did not intend to use this skill, creating privacy and integrity risks through mistaken activation.
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 88% confidence
Finding: The primary command trigger "track subscriptions" is relatively generic and does not encode any explicit scoping or confirmation requirements, which can cause the skill to activate in unintended contexts. In a finance-related skill, accidental activation can expose or process sensitive spending and subscription data when the user did not intend to invoke this capability.
Content: No source excerpt is available for this finding.

Missing User Warnings

Medium

Category: Not specified by scanner
Confidence: 92% confidence
Finding: This code path removes a subscription from the stored dataset and writes the change back to disk immediately when --permanent is used. Although it prints a message after deletion, there is no prior confirmation prompt or explicit warning at the point of execution for this irreversible local data loss operation.
Content: No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.