cisco-ai-defense/skill-scanner
Scans skills for prompt injection, data exfiltration and malicious code (static, behavioral, LLM).
- Kind
- Setup
- Works with
- Claude Code
- Source
- Research catalog: links @ 59863015342a
- Path
- items/cisco-skill-scanner
- Topics
- LLM apps & RAG, Agents & MCP, Data analysis & BI
- Tags
- security-scanning
Credit
- Made by
- Cisco AI Defense
- Original
- github.com/cisco-ai-defense/skill-scanner
- License
- Apache-2.0
Listed by Skill Manifest; not made by us.
InstallCopy it from the source repository, or sign in and let the assistant adapt it for your project.
Install factsScanned 2 Nov 2026
- Adds
- Settings to merge into .claude/settings.json
- Runs scripts
- None found
- Uses the network
- None found
- Needs secrets
- None found
- Source revision
- 59863015342a
- Licence
- Unknown
- Last activity
- Unknown
- Review
- Reviewed
Found by a static scan of the stored text; nothing is run. “None found” is not a guarantee, so read what you install before you run it.
- The source states no licence
- The source's last activity is not known yet
# cisco-ai-defense/skill-scanner Scans skills for prompt injection, data exfiltration and malicious code (static, behavioral, LLM). Listed from the research catalog, owner's research of 1 Nov 2026; the original is linked, nothing is copied. URL: https://github.com/cisco-ai-defense/skill-scanner