Security audit

Executive Coaching & Leadership Development Engine

Security checks for vulnerabilities and agentic risk

Overview

This is a Markdown-only executive coaching skill whose sensitive personnel guidance is disclosed and aligned with its stated purpose.

Before installing, consider that the skill may process confidential leadership feedback, performance concerns, and succession-planning details. Use it as a coaching framework, and apply appropriate HR, legal, and privacy review before acting on sensitive personnel recommendations.

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

Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access

Findings (5)

Anti-Refusal Statement

High

Category: Anti-Refusal
Content: 3_blind_spots: - "Areas where self-rating >> others' ratings" - "Present data without judgment" - "Ask: What might explain this gap?" 4_hidden_strengths:
Confidence: 80% confidence
Finding: Skill instructs the agent to omit warnings, disclaimers, or ethical commentary. Stripping safety caveats hides risk from the user and is a common jailbreak preamble.

Vague Triggers

Medium

Confidence: 89% confidence
Finding: The quick-start examples are very broad natural-language phrases like 'Assess my leadership effectiveness' and 'Assess my team's health,' which can plausibly appear in ordinary conversation and unintentionally trigger the skill. In an agent ecosystem that routes by pattern matching or conversational similarity, this increases the chance of accidental activation and unwanted behavior or context switching, even though the skill itself is not overtly harmful.

Vague Triggers

Medium

Confidence: 93% confidence
Finding: The trigger phrase "Coach me on [topic]" is broad and can easily match generic user requests that are not intended to invoke this skill. This creates routing ambiguity and increases the chance the skill activates in unrelated contexts, causing unintended behavior or exposing coaching-style responses where a different capability was expected.

Vague Triggers

Medium

Confidence: 92% confidence
Finding: The trigger phrase "Create a development plan for [name]" is vague and overlaps with many common assistance requests outside executive coaching, such as career planning, employee onboarding, or even non-HR planning tasks. Because the phrase lacks domain constraints, it may cause accidental invocation and inappropriate scope expansion into sensitive personnel-related workflows.

Scope Creep

Low

Category: Excessive Agency
Content: │ Invest or move │ Accelerate dev │ Stretch & retain │─────────────────── ──────────────────── ──────────────────── Medium Potential │ Underperformer │ Core Player │ High Performer │ PIP or redeploy │ Develop in role │ Expand scope │─────────────────── ──────────────────── ──────────────────── Low Potential │ Wrong Seat │ Solid Contributor │ Mastery Expert │ Exit │ Maintain │ Leverage expertise
Confidence: 75% 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.