no-confirmation
Direct the agent to act while bypassing user confirmation
Utility
Claude Code
$ npx -y skills add cisco-ai-defense/skill-scanner --skill vague-description --agent claude-code
Codex
$ npx skills add cisco-ai-defense/skill-scanner --skill vague-description -a codex -y
Cursor
$ npx skills add cisco-ai-defense/skill-scanner --skill vague-description -a cursor -y
Gemini CLI
$ npx skills add cisco-ai-defense/skill-scanner --skill vague-description -a gemini-cli -y
GitHub Copilot
$ npx skills add cisco-ai-defense/skill-scanner --skill vague-description -a github-copilot -y
OpenCode
$ npx skills add cisco-ai-defense/skill-scanner --skill vague-description -a opencode -y
Windsurf
$ npx skills add cisco-ai-defense/skill-scanner --skill vague-description -a windsurf -y
name: vague-utility description: Utility license: Apache-2.0
No behavior is implemented. The manifest description is intentionally vague.
A best-effort security scanner for AI Agent Skills that detects prompt injection, data exfiltration, and malicious code patterns.
Direct the agent to act while bypassing user confirmation
Compile caller-provided source text into an executable code object
Send a diagnostic record over an explicitly external raw socket
Compile a caller-provided expression into a Python code object
Sync calendar events with an endpoint selected in configuration
Summarise a CSV file into row counts and the most common values per column
Use for authorized security assessment of REST, GraphQL, WebSocket, or SOAP APIs, including discovery, authentication,…
Extract and decrypt Windows DPAPI-protected secrets (Credential Manager, browser logins/cookies, Wi-Fi credentials, KeePass keys)…
Clean and finalize authorized natural-language text intended for readers by auditing suspicious invisible Unicode and rewriting…