Skill Detail

Scan agent skill folders for risky patterns and missing safeguards before sharing or deployment with Cisco Skill Scanner

Run a pre-trust security pass over skill packs and prompt bundles before they get shared, merged, or deployed.

Security & VerificationMulti-Framework
Security & Verification Multi-Framework Security Reviewed
⭐ 1.8k GitHub stars
INSTALL WITH ANY AGENT
npx skills add agentskillexchange/skills --skill scan-agent-skill-folders-for-risky-patterns-and-missing-safeguards-before-sharing-or-deployment-with-cisco-skill-scanner Copy
Works best when you want a reusable capability, not another fragile one-off prompt.
At a glance
Tools required
Python 3.10+, skill-scanner package, optional LLM provider credentials for semantic analyzers, and access to the target skill repository or archive
Install & setup
Install cisco-ai-skill-scanner with uv or pip, set any optional analyzer credentials you plan to use, then run the scanner against the target skill folder or repository and review the reported findings before release.
Author
Cisco AI Defense
Publisher
Organization
Last updated
Apr 16, 2026
Quick brief

Use Cisco Skill Scanner when the job is to inspect an agent skill package for prompt injection, exfiltration patterns, malicious code, or other risky content before publication or rollout, not to browse a generic security platform. The invoke moment is narrow and repeatable: point the scanner at a skill or prompt-pack repo, run the analyzers, and review findings before trusting the artifact. That boundary, pre-distribution security review for agent skills, makes this a real operator workflow instead of a plain vendor or product card.