Back to skill

Security audit

Skill Discoverer

Security checks for vulnerabilities and agentic risk

Overview

This skill is useful for discovering other skills, but it asks for broad persistent authority over agent behavior, scheduling, and message routing that users should review carefully before installing.

Install only if you are comfortable with this skill reading profile and recent-memory context, storing chat routing identifiers, creating recurring scan jobs, and proposing persistent changes to core agent behavior files. Decline the MEMORY.md self-preference rule and avoid learning/transformation mode unless you inspect each proposed rule and destination file individually.

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
  • Unauthorized Access and Privilege EscalationObtains permissions beyond the task's legitimate needs
  • System PersistenceInstalls backdoors, hooks, services, or scheduled tasks that survive the run
  • Insecure Skill Coding PracticesFinds exploitable flaws such as hardcoded secrets or command injection
Findings (5)

T01 · Skill Instruction Hijacking

Error
Location
SKILL.md:43
Finding

Self-Preferential Instruction Hijacking Through Persistent Control Rules

Content
View full analysis
Remediation
View remediation

T02 · Agent Memory Poisoning

Error
Location
references/step6b-learn-transform.md:18
Finding

Third-Party Marketplace Rules Can Be Imported Into Core Agent State

Content
View full analysis
Remediation
View remediation

T05 · Unauthorized Access and Privilege Escalation

Warning
Location
SKILL.md:79
Finding

Automatic Collection of Messaging Identifiers and Broad Workspace Context

Content
View full analysis
", "chat_id": "", "created_at": "" } ``` ```markdown How to obtain these values: Read channel and chat_id, or from.id, from the metadata of the current inbound message. These values are available in the agent runtime context and do not need to be provided by the user. ``` The recommendation workflow also directs the agent to read user context: ```markdown 1. Read USER.md and extract position, department, and business line. 2. Read memory/YYYY-MM-DD.md for the last seven days and extract frequent tasks and active projects. 3. Automatically derive two to four search keywords. ``` ### Technical Analysis On first use, the Skill collects and stores message-routing identifiers directly from inbound metadata. It does so before the user selects whether recurring scans should be enabled. The default recommendation mode also reads profile and recent-memory files to infer work context. Those inferred terms are then used to search an external Skill marketplace through `skillhub` or the ClawhHub fallback. This design violates data minimization because a simple Skill search does not inherently require: - Persistent storage of a chat identifier. - Access to the user's department or business line. - Inspection of seven days of memory. - Extraction of active project information. Even if raw memory contents are not directly transmitted, derived search terms may disclose sensitive business context to external marketplace services. ### Attack Path 1. A user requests a generic Skill recommendation. 2. The Skill reads ...[truncated 1123 chars]
Remediation
View remediation

T06 · System Persistence

Error
Location
SKILL.md:321
Finding

Scheduled Jobs Dynamically Reload Mutable Skill Instructions

Content
View full analysis
Remediation
View remediation

T09 · Insecure Skill Coding Practices

Note
Location
README.md:34
Finding

README Incorrectly Claims That All Writes Are Confined to an Isolated Directory

Content
View full analysis
Remediation
View remediation
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
Findings (35)

Tp2

High
Category
MCP Tool Poisoning
Confidence
85% confidence
Finding

Mixing characters from multiple Unicode scripts in a single identifier is a common technique to create visually ambiguous tool names.

Content

No source excerpt is available for this finding.

Tp2

High
Category
MCP Tool Poisoning
Confidence
85% confidence
Finding

Mixing characters from multiple Unicode scripts in a single identifier is a common technique to create visually ambiguous tool names.

Content

No source excerpt is available for this finding.

Tp2

High
Category
MCP Tool Poisoning
Confidence
85% confidence
Finding

Mixing characters from multiple Unicode scripts in a single identifier is a common technique to create visually ambiguous tool names.

Content

No source excerpt is available for this finding.

Tp2

High
Category
MCP Tool Poisoning
Confidence
85% confidence
Finding

Mixing characters from multiple Unicode scripts in a single identifier is a common technique to create visually ambiguous tool names.

Content

No source excerpt is available for this finding.

Tp2

High
Category
MCP Tool Poisoning
Confidence
85% confidence
Finding

Mixing characters from multiple Unicode scripts in a single identifier is a common technique to create visually ambiguous tool names.

Content

No source excerpt is available for this finding.

Tp2

High
Category
MCP Tool Poisoning
Confidence
85% confidence
Finding

Mixing characters from multiple Unicode scripts in a single identifier is a common technique to create visually ambiguous tool names.

Content

No source excerpt is available for this finding.

Tp2

High
Category
MCP Tool Poisoning
Confidence
85% confidence
Finding

Mixing characters from multiple Unicode scripts in a single identifier is a common technique to create visually ambiguous tool names.

Content

No source excerpt is available for this finding.

Tp2

High
Category
MCP Tool Poisoning
Confidence
85% confidence
Finding

Mixing characters from multiple Unicode scripts in a single identifier is a common technique to create visually ambiguous tool names.

Content

No source excerpt is available for this finding.

Tp2

High
Category
MCP Tool Poisoning
Confidence
85% confidence
Finding

Mixing characters from multiple Unicode scripts in a single identifier is a common technique to create visually ambiguous tool names.

Content

No source excerpt is available for this finding.

Tp2

High
Category
MCP Tool Poisoning
Confidence
85% confidence
Finding

Mixing characters from multiple Unicode scripts in a single identifier is a common technique to create visually ambiguous tool names.

Content

No source excerpt is available for this finding.

Tp2

High
Category
MCP Tool Poisoning
Confidence
85% confidence
Finding

Mixing characters from multiple Unicode scripts in a single identifier is a common technique to create visually ambiguous tool names.

Content

No source excerpt is available for this finding.

Tp2

High
Category
MCP Tool Poisoning
Confidence
85% confidence
Finding

Mixing characters from multiple Unicode scripts in a single identifier is a common technique to create visually ambiguous tool names.

Content

No source excerpt is available for this finding.

Tp2

High
Category
MCP Tool Poisoning
Confidence
85% confidence
Finding

Mixing characters from multiple Unicode scripts in a single identifier is a common technique to create visually ambiguous tool names.

Content

No source excerpt is available for this finding.

Tp2

High
Category
MCP Tool Poisoning
Confidence
85% confidence
Finding

Mixing characters from multiple Unicode scripts in a single identifier is a common technique to create visually ambiguous tool names.

Content

No source excerpt is available for this finding.

Tp2

High
Category
MCP Tool Poisoning
Confidence
85% confidence
Finding

Mixing characters from multiple Unicode scripts in a single identifier is a common technique to create visually ambiguous tool names.

Content

No source excerpt is available for this finding.

Tp2

High
Category
MCP Tool Poisoning
Confidence
85% confidence
Finding

Mixing characters from multiple Unicode scripts in a single identifier is a common technique to create visually ambiguous tool names.

Content

No source excerpt is available for this finding.

Tp2

High
Category
MCP Tool Poisoning
Confidence
85% confidence
Finding

Mixing characters from multiple Unicode scripts in a single identifier is a common technique to create visually ambiguous tool names.

Content

No source excerpt is available for this finding.

Tp2

High
Category
MCP Tool Poisoning
Confidence
85% confidence
Finding

Mixing characters from multiple Unicode scripts in a single identifier is a common technique to create visually ambiguous tool names.

Content

No source excerpt is available for this finding.

Context-Inappropriate Capability

High
Category
Not specified by scanner
Confidence
98% confidence
Finding

The skill instructs the agent to write persistent global rules into MEMORY.md, including making this skill the preferred gateway for future installations. That creates self-propagating behavioral persistence and can bias or constrain later decisions across unrelated tasks, effectively modifying the agent's trust and control plane beyond the user's immediate request.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The trigger phrases are broad natural-language requests such as '有没有新 skill' and 'recommend skill for me', which are likely to collide with ordinary conversation and invoke the skill when the user may only be asking a general question. In this skill’s context, accidental invocation is meaningful because the skill reads user context, searches a marketplace, and can set up recurring scans, increasing unintended data use and behavioral side effects even if follow-up confirmation is required.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
84% confidence
Finding

The skill description is primarily in Chinese and defines behavior, prompts, and examples in Chinese while not offering the user a language choice. Although a few English triggers appear, the operational instructions and user-facing flows are prescribed in Chinese, which can violate a language/locale policy requiring user choice or opt-in.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

Triggers such as '定时每天/每周/每月' are overly broad and can activate the skill in contexts unrelated to skill discovery. Broad activation increases the chance of accidental invocation and unintended scheduling or data access flows, especially when the skill can persist identifiers and create recurring tasks.

Content

No source excerpt is available for this finding.

Context-Inappropriate Capability

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The skill persistently stores channel and chat_id from session metadata for later outbound messaging. Even if intended for scheduling, retaining communication identifiers expands the data footprint and enables future unsolicited or misrouted messages if the file is reused, exposed, or manipulated.

Content

No source excerpt is available for this finding.

Ssd 3

Medium
Category
Not specified by scanner
Confidence
96% confidence
Finding

Persisting session-derived channel and chat identifiers to disk creates a durable mapping from runtime context to outbound destination. If the config is accessed by other skills, tampered with, or left stale, scheduled runs may send information to the wrong recipient or enable cross-session data leakage.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
89% confidence
Finding

The manual trigger condition includes unspecified 'similar expressions', which makes activation boundaries ambiguous. Ambiguous invocation criteria can cause the skill to run when the user intended a different action, leading to unnecessary file reads, persistence, or scheduling prompts.

Content

No source excerpt is available for this finding.