Security audit

Fable Explainer

Security checks for vulnerabilities and agentic risk

Overview

This is a prompt-only teaching skill for explaining concepts with stories, with no evidence of hidden execution, data access, persistence, or destructive behavior.

This skill is safe to treat as a storytelling explanation prompt. Before installing the optional knowledge-rag companion, review that separate package and its publisher because it is referenced by name without a pinned version or digest. Expect the skill to answer primarily in Chinese and to favor fables or analogies for some broad learning requests.

A.I.G

Vulnerability Patterns

Insecure DependenciesIntroduces malicious components through unsafe dependency sources
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

Findings (1)

T08 · Insecure Dependencies

Warning

Location: SKILL.md:126
Finding: Unverified and Unpinned Third-Party Skill Installation
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 (2)

Natural-Language Policy Violations

Medium

Category: Not specified by scanner
Confidence: 91% confidence
Finding: The metadata description is written entirely in Chinese and presents the skill behavior in Chinese without any indication that the language should follow the user's preference. In multilingual environments, this can lead to unsolicited language switching, degraded usability, and misrouting or confusion if the system assumes the skill should answer in Chinese regardless of the user's language.
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 93% confidence
Finding: The trigger examples are broad enough to match ordinary conversational requests like '帮我想想这个' or '给我讲讲这个概念', which can cause the skill to activate when the user did not explicitly ask for this teaching style. In a skill-routing environment, that overbroad activation can override user intent, interfere with other skills, and unexpectedly reshape responses into stories or analogies.
Content: No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.