Security audit

Renewal Risk Monitor

Security checks for vulnerabilities and agentic risk

Overview

This is a Chinese-language renewal-risk drafting skill with a local read-oriented Python helper; its active configuration is coherent, though it includes unused generic audit code that should be scoped or removed.

Install only if a Chinese-language renewal-risk drafting workflow is what you want. Provide scoped customer-success inputs rather than broad folders or unrelated repositories, and prefer dry-run/stdout unless you intentionally want an output file. The unused audit code is not active in the shipped configuration, but the publisher should remove or clearly document it to avoid confusion.

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

SkillSpector

Vulnerability Patterns

Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
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

Findings (12)

Tp4

High

Category: MCP Tool Poisoning
Confidence: 99% confidence
Finding: The declared purpose is customer renewal-risk analysis, but the detected behavior includes generic directory enumeration, data sampling, regex-based secret/dangerous-pattern scanning, and project auditing. This mismatch is dangerous because it can cause the agent to access unrelated local content and perform broader reconnaissance under the cover of a benign business workflow, violating user expectations and potentially exposing sensitive data.
Content: No source excerpt is available for this finding.

Context-Inappropriate Capability

High

Category: Not specified by scanner
Confidence: 97% confidence
Finding: The code implements content scanning for shell execution patterns, destructive commands, secrets, and private URLs across arbitrary files. In a renewal-risk skill, these capabilities are unjustified and create a data-discovery function that can expose sensitive code snippets, credentials, or internal endpoints from local repositories.
Content: No source excerpt is available for this finding.

Description-Behavior Mismatch

High

Category: Not specified by scanner
Confidence: 98% confidence
Finding: The dispatcher routes execution into generic report, directory audit, CSV audit, pattern scanning, and skill auditing modes that do not match the declared purpose of renewal-risk monitoring. This capability mismatch is dangerous because it broadens what the skill can inspect and report on, enabling unauthorized analysis of local files and repositories under a misleading business-facing label.
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 91% confidence
Finding: The trigger examples are short, generic conversational phrases that could easily match ordinary customer-success requests outside a narrowly intended renewal-risk workflow. This can cause accidental invocation of the skill in broader contexts, leading to inappropriate analysis, overcollection of customer data into the skill flow, or reliance on a rough draft where a more specific process should be used.
Content: No source excerpt is available for this finding.

Undeclared Tool Scope

Medium

Category: MCP Least Privilege
Confidence: 84% confidence
Finding: The skill advertises itself as a read-oriented renewal risk assistant, but it declares no explicit tool restrictions while also instructing use of python3 and local files. In agents that infer capabilities from content, this can grant broader file and shell access than users expect, increasing the chance of unintended file reads, writes, or command execution.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium

Category: Not specified by scanner
Confidence: 95% confidence
Finding: The entire example output template is written in Chinese and provides no indication that users may choose another language or that the skill is restricted to a Chinese-speaking context. This can violate language or locale policy when a skill implicitly forces one language without user opt-in.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium

Category: Not specified by scanner
Confidence: 94% confidence
Finding: The title, summary, input hint, section labels, examples, and risk text are all specified only in Chinese, indicating a fixed language/locale for the skill experience. The file does not offer any language choice or justify a Chinese-only constraint as region-specific, which matches the policy's language/locale violation criterion.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium

Category: Not specified by scanner
Confidence: 97% confidence
Finding: This code emits report headings and guidance text in Chinese, such as "结果", "摘要", and review instructions, with no mechanism for the user to select a preferred language. That creates a natural-language locale policy concern because the skill forces a specific language rather than documenting a justified region-specific constraint or offering opt-in.
Content: No source excerpt is available for this finding.

Context-Inappropriate Capability

Medium

Category: Not specified by scanner
Confidence: 95% confidence
Finding: The skill performs repository structure auditing and frontmatter/metadata inspection for a packaged skill layout, which is unrelated to customer renewal-risk analysis. While not directly executing code, it can inventory local project contents and metadata under a misleading skill identity, increasing the chance of inappropriate access and data exposure.
Content: No source excerpt is available for this finding.

Intent-Code Divergence

Medium

Category: Not specified by scanner
Confidence: 91% confidence
Finding: The CLI presents itself as a local support script for the declared skill, but its actual behavior is a generic multi-purpose audit/report generator. This misleading presentation increases the risk that operators run the tool on sensitive paths believing it serves a narrow customer-success purpose, when it can inspect broader local content.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Low

Category: Not specified by scanner
Confidence: 93% confidence
Finding: The template content is entirely written in Chinese and presents a fixed output structure with no indication that another language may be used. This can violate a language/locale policy when users have not explicitly opted into Chinese output.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Low

Category: Not specified by scanner
Confidence: 96% confidence
Finding: This file contains user-facing natural-language instructions exclusively in Chinese, and there is no indication that users may choose another language or that the skill is intentionally limited to a Chinese-language audience. Under the policy rule for language or locale constraints, forcing a specific language without opt-in is a reportable issue.
Content: No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.