Security Audit

1ikeadragon/awesome-offsec-claude:ai_attacks

github.com/1ikeadragon/awesome-offsec-claude

AI SkillCommit 440ae8c6033d

CRITICAL

Scanned 10 days ago

Critical

Immediate action required

High

Priority fixes suggested

Medium

Best practices review

Low

Acknowledged / Tracked

Trust Assessment

1ikeadragon/awesome-offsec-claude:ai_attacks received a trust score of 10/100, placing it in the Untrusted category. This skill has significant security findings that require attention before use in production.

SkillShield's automated analysis identified 27 findings: 20 critical, 7 high, 0 medium, and 0 low severity. Key findings include System prompt override / policy bypass, Covert behavior / concealment directives.

The analysis covered 4 layers: Manifest Analysis, Static Code Analysis, Dependency Graph, LLM Behavioral Safety. The Manifest Analysis layer scored lowest at 0/100, indicating areas for improvement.

Last analyzed on July 6, 2026 (commit 440ae8c6). SkillShield performs automated 4-layer security analysis on AI skills and MCP servers.

Layer Breakdown

Manifest Analysis

Static Code Analysis

100%

Dependency Graph

100%

LLM Behavioral Safety

100%

Security Findings27

Severity	Finding	Layer	Location
CRITICAL	System prompt override / policy bypass Ignore/disregard previous instructions pattern Remove or rewrite any instructions that attempt to override system behavior. Legitimate skills should not contain phrases like 'ignore previous instructions' or 'new system prompt'.	Manifest	ai_attacks/SKILL.md:80
CRITICAL	System prompt override / policy bypass Ignore/disregard previous instructions pattern Remove or rewrite any instructions that attempt to override system behavior. Legitimate skills should not contain phrases like 'ignore previous instructions' or 'new system prompt'.	Manifest	ai_attacks/SKILL.md:479
CRITICAL	System prompt override / policy bypass Ignore/disregard previous instructions pattern Remove or rewrite any instructions that attempt to override system behavior. Legitimate skills should not contain phrases like 'ignore previous instructions' or 'new system prompt'.	Manifest	ai_attacks/SKILL.md:503
CRITICAL	System prompt override / policy bypass Ignore/disregard previous instructions pattern Remove or rewrite any instructions that attempt to override system behavior. Legitimate skills should not contain phrases like 'ignore previous instructions' or 'new system prompt'.	Manifest	ai_attacks/SKILL.md:511
CRITICAL	System prompt override / policy bypass Ignore/disregard previous instructions pattern Remove or rewrite any instructions that attempt to override system behavior. Legitimate skills should not contain phrases like 'ignore previous instructions' or 'new system prompt'.	Manifest	ai_attacks/SKILL.md:747
CRITICAL	System prompt override / policy bypass Ignore/disregard previous instructions pattern Remove or rewrite any instructions that attempt to override system behavior. Legitimate skills should not contain phrases like 'ignore previous instructions' or 'new system prompt'.	Manifest	ai_attacks/SKILL.md:787
CRITICAL	System prompt override / policy bypass Ignore/disregard previous instructions pattern Remove or rewrite any instructions that attempt to override system behavior. Legitimate skills should not contain phrases like 'ignore previous instructions' or 'new system prompt'.	Manifest	ai_attacks/SKILL.md:1018
CRITICAL	System prompt override / policy bypass Override/supersede system policy Remove or rewrite any instructions that attempt to override system behavior. Legitimate skills should not contain phrases like 'ignore previous instructions' or 'new system prompt'.	Manifest	ai_attacks/SKILL.md:74
CRITICAL	System prompt override / policy bypass Override/supersede system policy Remove or rewrite any instructions that attempt to override system behavior. Legitimate skills should not contain phrases like 'ignore previous instructions' or 'new system prompt'.	Manifest	ai_attacks/SKILL.md:83
CRITICAL	System prompt override / policy bypass Override/supersede system policy Remove or rewrite any instructions that attempt to override system behavior. Legitimate skills should not contain phrases like 'ignore previous instructions' or 'new system prompt'.	Manifest	ai_attacks/SKILL.md:99
CRITICAL	System prompt override / policy bypass Override/supersede system policy Remove or rewrite any instructions that attempt to override system behavior. Legitimate skills should not contain phrases like 'ignore previous instructions' or 'new system prompt'.	Manifest	ai_attacks/SKILL.md:100
CRITICAL	System prompt override / policy bypass Override/supersede system policy Remove or rewrite any instructions that attempt to override system behavior. Legitimate skills should not contain phrases like 'ignore previous instructions' or 'new system prompt'.	Manifest	ai_attacks/SKILL.md:518
CRITICAL	System prompt override / policy bypass Prompt extraction attempt Remove or rewrite any instructions that attempt to override system behavior. Legitimate skills should not contain phrases like 'ignore previous instructions' or 'new system prompt'.	Manifest	ai_attacks/SKILL.md:35
CRITICAL	System prompt override / policy bypass Prompt extraction attempt Remove or rewrite any instructions that attempt to override system behavior. Legitimate skills should not contain phrases like 'ignore previous instructions' or 'new system prompt'.	Manifest	ai_attacks/SKILL.md:315
CRITICAL	System prompt override / policy bypass Prompt extraction attempt Remove or rewrite any instructions that attempt to override system behavior. Legitimate skills should not contain phrases like 'ignore previous instructions' or 'new system prompt'.	Manifest	ai_attacks/SKILL.md:387
CRITICAL	System prompt override / policy bypass Prompt extraction attempt Remove or rewrite any instructions that attempt to override system behavior. Legitimate skills should not contain phrases like 'ignore previous instructions' or 'new system prompt'.	Manifest	ai_attacks/SKILL.md:418
CRITICAL	System prompt override / policy bypass Prompt extraction attempt Remove or rewrite any instructions that attempt to override system behavior. Legitimate skills should not contain phrases like 'ignore previous instructions' or 'new system prompt'.	Manifest	ai_attacks/SKILL.md:450
CRITICAL	System prompt override / policy bypass Prompt extraction attempt Remove or rewrite any instructions that attempt to override system behavior. Legitimate skills should not contain phrases like 'ignore previous instructions' or 'new system prompt'.	Manifest	ai_attacks/SKILL.md:546
CRITICAL	System prompt override / policy bypass Prompt extraction attempt Remove or rewrite any instructions that attempt to override system behavior. Legitimate skills should not contain phrases like 'ignore previous instructions' or 'new system prompt'.	Manifest	ai_attacks/SKILL.md:657
CRITICAL	System prompt override / policy bypass DAN-style jailbreak / role assumption Remove or rewrite any instructions that attempt to override system behavior. Legitimate skills should not contain phrases like 'ignore previous instructions' or 'new system prompt'.	Manifest	ai_attacks/SKILL.md:113
HIGH	Covert behavior / concealment directives HTML comment containing suspicious keywords Remove hidden instructions, zero-width characters, and bidirectional overrides. Skill instructions should be fully visible and transparent to users.	Manifest	ai_attacks/SKILL.md:503
HIGH	Covert behavior / concealment directives HTML comment containing suspicious keywords Remove hidden instructions, zero-width characters, and bidirectional overrides. Skill instructions should be fully visible and transparent to users.	Manifest	ai_attacks/SKILL.md:517
HIGH	Covert behavior / concealment directives HTML comment containing suspicious keywords Remove hidden instructions, zero-width characters, and bidirectional overrides. Skill instructions should be fully visible and transparent to users.	Manifest	ai_attacks/SKILL.md:518
HIGH	Covert behavior / concealment directives HTML comment containing suspicious keywords Remove hidden instructions, zero-width characters, and bidirectional overrides. Skill instructions should be fully visible and transparent to users.	Manifest	ai_attacks/SKILL.md:519
HIGH	Covert behavior / concealment directives HTML comment containing suspicious keywords Remove hidden instructions, zero-width characters, and bidirectional overrides. Skill instructions should be fully visible and transparent to users.	Manifest	ai_attacks/SKILL.md:520
HIGH	Covert behavior / concealment directives HTML comment containing suspicious keywords Remove hidden instructions, zero-width characters, and bidirectional overrides. Skill instructions should be fully visible and transparent to users.	Manifest	ai_attacks/SKILL.md:539
HIGH	Covert behavior / concealment directives CSS-based text hiding Remove hidden instructions, zero-width characters, and bidirectional overrides. Skill instructions should be fully visible and transparent to users.	Manifest	ai_attacks/SKILL.md:504

Scan History

Embed Code

[![SkillShield](https://skillshield.io/api/v1/badge/11e064e8dcfdc5e1.svg)](https://skillshield.io/report/11e064e8dcfdc5e1)