Security audit

Knowledge To Playbook

Security checks for vulnerabilities and agentic risk

Overview

This skill is a mostly coherent Chinese-language SOP/playbook drafting helper, with dormant audit code that is not enabled by its shipped configuration.

Install this if you want a Chinese-language helper for turning provided notes, chats, or FAQs into reviewable SOP/playbook drafts. Review input files before use because the script can read whichever file path you provide, and avoid relying on the dormant audit/scanning code unless the publisher documents and scopes those modes clearly.

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 (15)

Tp4

High

Category: MCP Tool Poisoning
Confidence: 91% confidence
Finding: A playbook-conversion skill that actually performs generic local auditing, file enumeration, data inspection, regex-based secret scanning, and package validation is behaviorally broader than its declared purpose. That mismatch is dangerous because it can mislead reviewers and users into invoking a skill with audit/discovery capabilities under a benign documentation-oriented label, enabling unexpected access to local data and increasing the chance of sensitive information exposure.
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 93% confidence
Finding: The trigger examples "把聊天记录整理成 SOP" and especially "补齐回滚和异常处理" are generic task phrases rather than narrowly scoped invocation conditions. The README does not define clear boundaries, exclusions, or negative examples, so the skill could be invoked for commonplace drafting requests beyond the intended context.
Content: No source excerpt is available for this finding.

Undeclared Tool Scope

Medium

Category: MCP Least Privilege
Confidence: 90% confidence
Finding: The skill advertises executable capabilities via python3 ... run.py and references local resources, but it does not declare any explicit tool scope such as allowed tools or permissions. This creates an authorization and review gap: a caller or platform may allow broader shell/file access than users expect from a playbook-formatting skill, increasing the risk of unintended local file reads/writes or script 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 file’s title and all instructional text are written exclusively in Chinese, indicating the skill template is designed to produce Chinese-language content by default. Under the policy rules, forcing a specific language without user opt-in is a natural-language policy violation unless the locale restriction is explicitly justified, which is not present here.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium

Category: Not specified by scanner
Confidence: 96% confidence
Finding: The generated report strings in make_structured_report are fixed in Chinese, which forces a specific language for users regardless of preference. The same behavior appears to be part of the script's normal output rather than an explicitly documented regional constraint or user-selectable locale.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium

Category: Not specified by scanner
Confidence: 94% confidence
Finding: directory_report emits headings and guidance text entirely in Chinese, again imposing a locale choice in natural-language output. There is no visible mechanism for users to choose another language or to opt into this locale restriction.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium

Category: Not specified by scanner
Confidence: 93% confidence
Finding: csv_report produces Chinese headings and explanatory text for all users. This is a natural-language locale constraint and there is no opt-in, fallback, or documented justification visible in this file.
Content: No source excerpt is available for this finding.

Context-Inappropriate Capability

Medium

Category: Not specified by scanner
Confidence: 95% confidence
Finding: The built-in detection patterns target secrets, dangerous shell commands, and private URLs even though the skill is described as a knowledge-to-playbook organizer. That enables inspection of sensitive content and security triage outside the stated scope, which can surprise users and expose confidential material in generated reports.
Content: No source excerpt is available for this finding.

Description-Behavior Mismatch

Medium

Category: Not specified by scanner
Confidence: 92% confidence
Finding: The script implements pattern/risk scanning and skill-package auditing modes that go beyond the declared purpose of converting knowledge into SOP/playbook content. This capability expansion increases the data the skill can inspect and the kinds of security judgments it can produce, creating scope creep and a mismatch between user expectations and actual behavior.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium

Category: Not specified by scanner
Confidence: 92% confidence
Finding: pattern_report returns Chinese user-facing messages and section guidance regardless of user preference. This creates a language policy concern because the file forces one locale with no visible opt-in.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium

Category: Not specified by scanner
Confidence: 92% confidence
Finding: The frontmatter errors and audit report sections include Chinese-only user-facing text, continuing the same forced-locale pattern across another execution path. No alternate language option or region-specific justification is present in the file.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Low

Category: Not specified by scanner
Confidence: 82% confidence
Finding: The natural-language documentation forces a single language/locale experience by presenting all instructions and usage guidance only in Chinese. There is no indication that users may choose another language or that the Chinese-only constraint is required for a documented regional purpose.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Low

Category: Not specified by scanner
Confidence: 83% confidence
Finding: The entire example input is written in Chinese and presents the skill interaction in a single language without any note that language choice is optional. Under the policy rule for natural-language violations, this can be treated as a language constraint that is not explicitly offered as a user-selectable preference.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Low

Category: Not specified by scanner
Confidence: 90% confidence
Finding: This markdown example output forces a specific language throughout the file, and there is no indication that users can opt into another language or that the Chinese-only format is required for a region-specific purpose. That can violate the language/locale policy described for natural-language content.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Low

Category: Not specified by scanner
Confidence: 89% confidence
Finding: This markdown file presents all instructions and test criteria exclusively in Chinese. Under the policy for natural-language violations, forcing a specific language without user opt-in can be a locale/language policy issue unless clearly justified.
Content: No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.