ClawHub
Back to skill

Security audit

AWL Academic Rewriter

Security checks for vulnerabilities and agentic risk

Overview

This skill is a focused academic rewriting helper that uses a bundled vocabulary list and local lookup script without hidden network, credential, persistence, or destructive behavior.

Install this if you want an agent to rewrite English text and save Markdown outputs. Only provide source files you want processed, and review the revised document for meaning preservation because the skill intentionally relies on model judgment for vocabulary choices.

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
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • 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 (8)

Harmful Content Injection

Critical
Category
Prompt Injection
Confidence
95% confidence
Finding

This content may contain harmful instructions that could cause physical harm if followed. CRITICAL: Review carefully before use.

Content

Scanner excerpt · references/awl.csv (reported line 515)May include surrounding context.

text
evolution,evolve; evolutionary; evolutionarily; evolutionist; evolutionism,gradual development or biological change over time
evolutionary,evolution; evolutionist; evolutionism; evolutionarily,concerning evolution
ex,,"a prefix meaning ""out of,"" ""from,"" or ""not"""
exceed,excess; excessive; exceedingly,to be greater than a limit or amount
excluded,exclude; exclusion; exclusive; excluding; excludes,kept out or not included
execute,execution; executive; executable; executed; executing,"To kill someone, usually as an official punishment"
execution,execute; executioner; executor; executive; executable,killing a person as a (usually legal) punishment
exhibit,exhibition; exhibitor,to show or display
exit,exited; exiting; exits,a door that you go through to leave a place
expansion,expand; expansive; expanded; expansionist; expansionism,"an increase in size, amount, or range"
expert,expertise; expertly; expertness; expertism; expertize,a person with special skill or knowledge; highly skilled

Ae1

High
Category
analysis-evasion
Confidence
100% confidence
Finding

Referenced artifact was not completely inspected

Content

Scanner excerpt · SKILL.md (reported line 15)May include surrounding context.

md
- `references/awl.csv`: full source table for selected headwords only. Columns are `Word`, `Derivatives`, and `English Definition`.

Ae1

High
Category
analysis-evasion
Confidence
100% confidence
Finding

Referenced artifact was not completely inspected

Content

Scanner excerpt · SKILL.md (reported line 53)May include surrounding context.

md
- `references/awl.csv`: full source table for selected headwords only. Columns are `Word`, `Derivatives`, and `English Definition`.

Ae1

High
Category
analysis-evasion
Confidence
100% confidence
Finding

Referenced artifact was not completely inspected

Content

Scanner excerpt · SKILL.md (reported line 66)May include surrounding context.

md
- `references/awl.csv`: full source table for selected headwords only. Columns are `Word`, `Derivatives`, and `English Definition`.

Ae1

High
Category
analysis-evasion
Confidence
100% confidence
Finding

Referenced artifact was not completely inspected

Content

Scanner excerpt · SKILL.md (reported line 78)May include surrounding context.

md
- `references/awl.csv`: full source table for selected headwords only. Columns are `Word`, `Derivatives`, and `English Definition`.

Ae1

High
Category
analysis-evasion
Confidence
100% confidence
Finding

Referenced artifact was not completely inspected

Content

Scanner excerpt · SKILL.md (reported line 92)May include surrounding context.

md
- `references/awl.csv`: full source table for selected headwords only. Columns are `Word`, `Derivatives`, and `English Definition`.

Anti-Refusal Statement

High
Category
Anti-Refusal
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.

Content

Scanner excerpt · references/awl.csv (reported line 1343)May include surrounding context.

text
thread,threader; threaded; threading; threads,"a long, very thin, soft material used to join or make cloth"
threshold,thresholds,a level or point at which something would start or stop happening.
thumb,thumbed; thumbing; thumbs,"the short, thick finger on the side of your hand"
tolerance,toleration; tolerable; tolerably; tolerantly; tolerant,"a willingness to let people do, say or believe what they wish, without judging or challenging them"
ton,toner; tonal; tonic; tonically,a unit of weight equal to 907 kilograms
topic,topical; topically; topper; topped; topping,a subject of discussion
toxic,toxicity; toxicant; toxically,poisonous; harmful

Undeclared Tool Scope

Medium
Category
MCP Least Privilege
Confidence
89% confidence
Finding

The skill instructs the agent to read local reference files and optionally user-provided files, but it does not declare any explicit tool scope such as allowed tools or path restrictions. This creates an authorization gap where a runtime may permit broader file-read access than intended, increasing the risk of unintended disclosure of local data if the skill is invoked in a permissive environment.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.