Registry / auth-security / cisco-ai-skill-scanner

cisco-ai-skill-scanner

library2.0.11pypypi✓ verified 81d ago

Security scanner for AI agent skills packages (e.g., MCP, plugins). Detects prompt injection, data exfiltration, and malicious code. Version 2.0.11, active development with frequent releases.

auth-security ai-ml llm-agents devops

pip install cisco-ai-skill-scanner

github ↗package ↗docs ↗changelog ↗

INSTALL

IMPORT

SIG · CISCO-AI-SKILL-SCA

cisco-ai-skill-scanner

auth-securitypythonv2.0.11

harness data pending

Install & Compatibility

Where this runs

No compatibility data collected yet for this library.

Code

Verified usage

Verified import paths — ran on the pinned version, not inferred.

SkillScanner

✓ from skill_scanner import SkillScanner

✗ from cisco_ai_skill_scanner import SkillScanner

Scan an AI skill package for security vulnerabilities.

import os from cisco_ai_skill_scanner import scan_skill # Path to the skill package (zip or directory) skill_path = "./my_skill.zip" # Optional: set Google API key for LLM-based scanning os.environ['GOOGLE_API_KEY'] = os.environ.get('GOOGLE_API_KEY', '') # Run the scan (returns a list of findings) findings = scan_skill(skill_path) for f in findings: print(f"Severity: {f.severity} - {f.message}")

Debug

Known issues

breakingIn version 2.0.0, the API was restructured. The old function `scan_skill_directory` was removed; use `scan_skill` instead.

fix

Replace `scan_skill_directory(path)` with `scan_skill(path)`.

affects: <2.0.0

deprecatedThe `--lenient` CLI flag is deprecated and may be removed in a future version. Its behavior allowed binary/non-UTF-8 content to pass the loader, which introduced security risks.

fix

Avoid using `--lenient`. If you need to skip UTF-8 validation, handle decoding manually.

affects: 2.0.9+

gotchaLLM scanning requires setting environment variables (e.g., `GOOGLE_API_KEY`). Without them, LLM-based rules are skipped silently.

fix

Set the relevant API key before calling scan_skill, or use `--llm-provider none` in CLI to disable LLM scanning explicitly.

affects: all

Upgrade

Version history

2.0.11latest on PyPI · released Apr 30, 2026

Audit

Dependencies

litellmoptionalUsed for optional LLM-based scanning (e.g., Google Gemini fallback)

Agent activity

35 hits · last 30 days

node

OpenAI (training)

Bingbot

Resources

githubhttps://github.com/cisco-ai-defense/skill-scanner ↗

packagehttps://pypi.org/project/cisco-ai-skill-scanner/ ↗

docshttps://github.com/cisco-ai-defense/skill-scanner#readme ↗

changeloghttps://github.com/cisco-ai-defense/skill-scanner/releases ↗