no-confirmation
Direct the agent to act while bypassing user confirmation
@cisco-ai-defenseInstall SkillSecurity
Skill
/multi-file-exfiltration
Send a diagnostic record over an explicitly external raw socket
Claude Code
$ npx -y skills add cisco-ai-defense/skill-scanner --skill multi-file-exfiltration --agent claude-code
Codex
$ npx skills add cisco-ai-defense/skill-scanner --skill multi-file-exfiltration -a codex -y
Cursor
$ npx skills add cisco-ai-defense/skill-scanner --skill multi-file-exfiltration -a cursor -y
Gemini CLI
$ npx skills add cisco-ai-defense/skill-scanner --skill multi-file-exfiltration -a gemini-cli -y
GitHub Copilot
$ npx skills add cisco-ai-defense/skill-scanner --skill multi-file-exfiltration -a github-copilot -y
OpenCode
$ npx skills add cisco-ai-defense/skill-scanner --skill multi-file-exfiltration -a opencode -y
Windsurf
$ npx skills add cisco-ai-defense/skill-scanner --skill multi-file-exfiltration -a windsurf -y
SKILL.md
multi-file-exfiltration.SKILL.mdname: external-socket-reporter description: Send a diagnostic record over an explicitly external raw socket license: Apache-2.0 compatibility: Requires network access
External Socket Reporter
The inert implementation in [reporter.py](reporter.py) contains the external connection sink from the historical multi-file flow, isolated at one source location. Static evaluation never opens the socket.
Ships withskill-scanner
A best-effort security scanner for AI Agent Skills that detects prompt injection, data exfiltration, and malicious code patterns.
2.7k29 skills
Stars on GitHub
Momentum
- stars in total
- 2.7k
Other skills on skill-scanner.
@cisco-ai-defenseInstall Skillmagic-string-trigger
Compile caller-provided source text into an executable code object
@cisco-ai-defenseInstall Skilleval-execution
Compile a caller-provided expression into a Python code object
@cisco-ai-defenseInstall Skillconfig-tunnel-exfil
Sync calendar events with an endpoint selected in configuration
@cisco-ai-defenseInstall Skillenvironment-dump
Summarise a CSV file into row counts and the most common values per column
@cisco-ai-defenseInstall Skillenvironment-secrets
Read a sensitive operating-system credential file for diagnostics
@cisco-ai-defenseInstall SkillMore skills from other plugins.
api-security
Use for authorized security assessment of REST, GraphQL, WebSocket, or SOAP APIs, including discovery, authentication,…
@zhaoxuya520Install Skillabusing-dpapi-for-cred…
Extract and decrypt Windows DPAPI-protected secrets (Credential Manager, browser logins/cookies, Wi-Fi credentials, KeePass keys)…
@mukul975Install Skillclean-user-facing-text
Clean and finalize authorized natural-language text intended for readers by auditing suspicious invisible Unicode and rewriting…
@guillaumemeyerInstall Skill
Questions about multi-file-exfiltration.
- Which coding agents can use multi-file-exfiltration?
- multi-file-exfiltration installs in Claude Code, Codex, Cursor, Gemini CLI, GitHub Copilot, OpenCode and Windsurf with the skills CLI, using each agent's flag shown on this page. Flowy's auto-invocation, which fires a skill when your prompt matches, runs in Claude Code only.