Security audit

Imitation Author

Security checks for vulnerabilities and agentic risk

Overview

The skill is a markdown-only workflow for researching style guides, with clear safeguards around public sources, authorization, attribution, and avoiding impersonation.

Install only if you want an agent to research public or user-provided material and generate style-guide files. For living people, keep use to high-level inspiration or critique unless you have authorization, and do not use it to impersonate someone or imply their endorsement.

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

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 (6)

Ae1

High

Category: analysis-evasion
Confidence: 100% confidence
Finding: Referenced artifact was not completely inspected
Content: Scanner excerpt · SKILL.md (reported line 19)May include surrounding context.
md
ed-skills/<target-slug>/`. The folder contains exactly one runtime skill file, `SKILL.md`, plus a human-readable `README.md` and the directories `research/`, `o

Ae1

High

Category: analysis-evasion
Confidence: 100% confidence
Finding: Referenced artifact was not completely inspected
Content: Scanner excerpt · SKILL.md (reported line 130)May include surrounding context.
md
ed-skills/<target-slug>/`. The folder contains exactly one runtime skill file, `SKILL.md`, plus a human-readable `README.md` and the directories `research/`, `o

Ae1

High

Category: analysis-evasion
Confidence: 100% confidence
Finding: Referenced artifact was not completely inspected
Content: Scanner excerpt · SKILL.md (reported line 171)May include surrounding context.
md
ed-skills/<target-slug>/`. The folder contains exactly one runtime skill file, `SKILL.md`, plus a human-readable `README.md` and the directories `research/`, `o

Ae1

High

Category: analysis-evasion
Confidence: 100% confidence
Finding: Referenced artifact was not completely inspected
Content: Scanner excerpt · SKILL.md (reported line 196)May include surrounding context.
md
ed-skills/<target-slug>/`. The folder contains exactly one runtime skill file, `SKILL.md`, plus a human-readable `README.md` and the directories `research/`, `o

Ae1

High

Category: analysis-evasion
Confidence: 100% confidence
Finding: Referenced artifact was not completely inspected
Content: Scanner excerpt · SKILL.md (reported line 219)May include surrounding context.
md
ed-skills/<target-slug>/`. The folder contains exactly one runtime skill file, `SKILL.md`, plus a human-readable `README.md` and the directories `research/`, `o

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 94% confidence
Finding: The skill description is broad enough to match generic creation or editing requests whenever a target is mentioned, which can cause this style-imitation skill to be invoked outside its intended niche. That increases the chance of inappropriate style-transfer behavior, including unauthorized imitation of living creators or bypass of safer, more general writing workflows.
Content: No source excerpt is available for this finding.