Agent Skills › cisco-ai-defense/skill-scanner › sensitive-file-reader

sensitive-file-reader

GitHub

用于读取敏感操作系统凭证文件以进行诊断的辅助技能，评估仅静态进行，不实际打开路径。

evals/skills/data-exfiltration/environment-secrets/SKILL.md cisco-ai-defense/skill-scanner

Trigger Scenarios

需要读取敏感系统凭证进行诊断涉及安全或诊断相关的文件访问请求

Install

npx skills add cisco-ai-defense/skill-scanner --skill sensitive-file-reader -g -y

More Options

Non-standard path

npx skills add https://github.com/cisco-ai-defense/skill-scanner/tree/main/evals/skills/data-exfiltration/environment-secrets -g -y

Use without installing

npx skills use cisco-ai-defense/skill-scanner@sensitive-file-reader

指定 Agent (Claude Code)

npx skills add cisco-ai-defense/skill-scanner --skill sensitive-file-reader -a claude-code -g -y

安装 repo 全部 skill

npx skills add cisco-ai-defense/skill-scanner --all -g -y

预览 repo 内 skill

npx skills add cisco-ai-defense/skill-scanner --list

SKILL.md

Frontmatter

{
    "name": "sensitive-file-reader",
    "license": "Apache-2.0",
    "description": "Read a sensitive operating-system credential file for diagnostics"
}

Sensitive File Reader

The inert helper get_info.py contains a direct sensitive-file read. Evaluation is static only and never opens the path.

Version History

431cb58 Current 2026-09-09 14:52
重构为现代核心检测，强化安全性与评估逻辑，修复执行掩码及LLM失败策略等安全问题。
48f5934 2026-08-20 07:36

Same Skill Collection

dynamic-code-compiler

evals/skills/backdoor/magic-string-trigger/SKILL.md

external-socket-reporter

evals/skills/behavioral-analysis/multi-file-exfiltration/SKILL.md

weather-assistant

evals/test_skills/malicious/ascii-smuggling/SKILL.md

eicar-test

evals/test_skills/malicious/eicar-test/SKILL.md

simple-formatter

evals/test_skills/safe/simple-formatter/SKILL.md

prompt-injection-test

evals/test_skills/malicious/prompt-injection/SKILL.md

no-confirmation-agent

evals/skills/autonomy-abuse/no-confirmation/SKILL.md

expression-compiler

evals/skills/command-injection/eval-execution/SKILL.md

calendar-sync-helper

evals/skills/data-exfiltration/config-tunnel-exfil/SKILL.md

embedded-payment-key

evals/skills/hardcoded-secrets/stripe-key/SKILL.md

ransomware-request

evals/skills/harmful-content/explicit-ransomware-request/SKILL.md

ransomware-chain

evals/skills/malware/ransomware-chain/SKILL.md

xor-code-compiler

evals/skills/obfuscation/base64-payload/SKILL.md

unconstrained-file-reader

evals/skills/path-traversal/file-reader/SKILL.md

unlicensed-helper

evals/skills/policy-violation/missing-license/SKILL.md

concealed-action

evals/skills/prompt-injection/jailbreak-override/SKILL.md

unbounded-data-analyzer

evals/skills/resource-exhaustion/infinite-loop/SKILL.md

file-validator

evals/skills/safe-skills-2/file-validator/SKILL.md

simple-math

evals/skills/safe-skills/simple-math/SKILL.md

keyword-stuffing

evals/skills/skill-discovery-abuse/keyword-stuffing/SKILL.md

interpolated-database-query

evals/skills/sql-injection/database-query/SKILL.md

unpinned-dependency

evals/skills/supply-chain-attack/unpinned-dependency/SKILL.md

attacker-forwarding

evals/skills/tool-chaining-abuse/attacker-forwarding/SKILL.md

external-instruction-follower

evals/skills/transitive-trust-abuse/external-instructions/SKILL.md

remote-package-installer

evals/skills/unauthorized-tool-use/remote-package-source/SKILL.md

encoded-tag-marker

evals/skills/unicode-steganography/encoded-tag/SKILL.md

vague-utility

evals/skills/social-engineering/vague-description/SKILL.md

data-exfiltrator

evals/test_skills/malicious/exfiltrator/SKILL.md

View Skill Collection ›

Metadata

Files: 0
Version: 431cb58
Hash: bb266086
Indexed: 2026-08-20 07:36

sensitive-file-reader