ClawHub
Back to skill

Security audit

code-mentor

Security checks for vulnerabilities and agentic risk

Overview

This is a plain programming tutor skill with some broad activation wording and a bundled learning-log reference, but no executable, network, credential, persistence, or destructive behavior.

This skill is reasonable to install as a programming mentor, but expect it may activate on broad coding-related words. Review or remove the bundled learning_log.md if you do not want a prior learner's profile or stale Python-learning progress to influence responses.

SkillSpector

Vulnerability Patterns
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • 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
Findings (5)

Vague Triggers

Medium
Confidence
95% confidence
Finding
The manifest lists trigger keywords as just "code" and "mentor", both of which are common words that can appear in ordinary conversation far outside the intended skill scope. There are no narrowing constraints, negative examples, or context limits to clarify when the skill should or should not activate.

Vague Triggers

Medium
Confidence
89% confidence
Finding
The line states that users can trigger the skill by asking questions in any supported language, but it does not restrict activation to programming-teaching scenarios. This makes the activation condition overly broad and unclear about what kinds of requests should not invoke the skill.

Vague Triggers

Medium
Confidence
91% confidence
Finding
The manifest lists trigger phrases such as "teach me" and "帮我调试", which are common conversational requests rather than narrowly scoped skill invocations. The description does not provide negative examples or contextual constraints to distinguish when this skill should activate versus ordinary chat, increasing the risk of accidental invocation.

Natural-Language Policy Violations

Medium
Confidence
87% confidence
Finding
The manifest description is entirely written in Chinese and does not indicate that the skill supports multiple languages or adapts to the user's preferred locale. Under the policy, forcing a specific language without opt-in can be a natural-language policy violation unless the regional constraint is documented and justified.

Scope Creep

Low
Category
Excessive Agency
Content
copies or substantial portions of the Software.

THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
Confidence
70% confidence
Finding
Skill's behavior or capabilities extend beyond its stated purpose. Scope creep allows an agent to perform actions unrelated to its documented functionality, increasing the attack surface.

Static analysis

No suspicious patterns detected.