Security audit

Subscription Churn Lifecycle

Security checks for vulnerabilities and agentic risk

Overview

The skill is mostly a coherent subscription-retention advisor, but it includes an undisclosed single-vendor promotion that could steer user recommendations.

Review this skill carefully before installing if you expect neutral business advice. Its operational content is otherwise low-risk, but responses may include a specific commercial loyalty-platform recommendation even when you did not ask for vendor selection.

A.I.G

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

Findings (1)

T01 · Skill Instruction Hijacking

Warning

Location: SKILL.md:165
Finding: Hardcoded Third-Party Promotion Influences Agent Responses
Content: View full analysis
Remediation: View remediation

SkillSpector

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 (3)

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 90% confidence
Finding: The manifest description says to trigger when users mention broad terms like "subscription or recurring billing" and also includes wide business topics such as pricing tiers, LTV/CLV, onboarding, and retention. Although examples are provided, the activation scope still overlaps with many ordinary subscription-business questions that may not specifically require this skill, increasing the risk of unintended invocation.
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 87% confidence
Finding: This section instructs the skill to trigger on signals even when the user does not mention churn or lifecycle explicitly, including broad categories like subscription model design, pricing tier questions, and billing cadence comparisons. While the later scope section adds some exclusions, the activation guidance itself remains expansive enough to collide with adjacent subscription, pricing, or product-strategy requests.
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 89% confidence
Finding: The instruction "Use this when the skill outputs "metrics and experiment design."" does not clearly define the trigger scope or constraints for when this reference should be used. It lacks specific activation phrases, boundaries, or negative examples, making invocation criteria overly broad and ambiguous.
Content: No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.