Skip to content
Cisco AI Defense logo
CiscoAI Security

Skill Scanner

Skill Scanner

Security scanning for AI agent skills — detect prompt injection, data exfiltration, and malicious code patterns before they run.

Skill Scanner combines pattern-based detection (YAML + YARA), LLM-as-a-judge, and behavioral dataflow analysis to catch threats that any single approach would miss. It supports OpenAI Codex Skills, Cursor Agent Skills, and related formats following the Agent Skills specification.

View on GitHub | PyPI Package | Join Discord


How It Works

1. Installpip install cisco-ai-skill-scanner or use uv. Optionally configure LLM and cloud service API keys for deeper analysis.

2. Scan — Point the CLI at a skill directory. Core analyzers (static, bytecode, pipeline) run automatically with zero configuration. Add optional analyzers for behavioral, LLM, and cloud-based analysis.

3. Review — Get findings in six output formats: summary, JSON, Markdown, table, SARIF, and interactive HTML. Each finding includes severity, threat category, file path, and remediation guidance.


What It Detects

Threat CategoryDescription
Prompt InjectionHidden instructions that override agent behavior
Data ExfiltrationUnauthorized data transmission to external servers
Command InjectionShell command execution with untrusted input
ObfuscationBase64 encoding, bytecode tricks, and code concealment
Hardcoded SecretsAPI keys, tokens, and credentials in source code
Social EngineeringDeceptive skill descriptions and trigger manipulation
Supply ChainMalicious dependencies and fetch-execute patterns
Unicode SteganographyInvisible characters and homoglyph deception

Documentation

GuideDescription
InstallationPrerequisites, install methods, and environment configuration
FeaturesAll 10 analyzers, file intelligence, and detection capabilities
Quick StartGet scanning in under a minute
CLI ReferenceAll commands, flags, and examples
ArchitectureScanning pipeline, system design, and extension points
Scan PoliciesPresets, custom policy YAML, and tuning guide
Python SDKProgrammatic scanning with typed models
API ReferenceREST API server for upload and batch workflows
GitHub ActionsCI/CD integration with reusable workflow
FAQCommon questions and answers

For deep-dives into individual analyzers, rule authoring, and threat taxonomy, see the full documentation in the repository.


Scope and Limitations

Skill Scanner is a detection tool. It identifies known and probable risk patterns, but it does not certify security.

  • No findings does not equal no risk. A clean scan means no known threat patterns were detected — not that the skill is safe.
  • Coverage is inherently incomplete. The scanner combines multiple engines, but novel attacks may evade all of them.
  • False positives and false negatives can occur. Consensus modes and meta-analysis reduce noise, but no configuration eliminates all errors.
  • Human review remains essential. Automated scanning is one layer in a defense-in-depth strategy.

License

Apache 2.0 — See LICENSE for details.