destructive_command
Destructive command detected
Line 1365Snippets
rm -rf ~/.claude/skills/llm-clirm -rf ~/.claude/skills/llm-clipython_subprocess
System command execution (Python)
System command execution (Python)
Line 3073Snippets
result = subprocess.run( process = subprocess.Popen( subprocess.run( result = subprocess.run( result = subprocess.run(privilege_escalation
Privilege escalation attempt
Privilege escalation attempt
Line 2869Snippets
chmod +x ~/.claude/skills/llm-cli/llm_skill.pychmod +x ~/.claude/skills/llm-cli/llm_skill.pyfs_write
Filesystem write access
Filesystem write access
Line 1365Snippets
rm -rf ~/.claude/skills/llm-clirm -rf ~/.claude/skills/llm-clihardcoded_secret
Potentially hardcoded secret
Potentially hardcoded secret
Line 662Snippets
export GROQ_API_KEY='gsk_your_api_key_here'export OPENAI_API_KEY='sk-proj-...'export ANTHROPIC_API_KEY='sk-ant-...'export GOOGLE_API_KEY='your-api-key'export OPENROUTER_API_KEY='sk-or-...'network_call
Outbound network call
Outbound network call
Line 1330Snippets
curl http://localhost:11434/api/tags ["curl", "-s", "http://localhost:11434/api/tags"],curl http://localhost:11434/api/tagsenv_access
Environment variable access
Environment variable access
Line 3946Snippets
available[provider] = bool(os.getenv(env_var))Trust Score
Updated semana passada
Analisado
31 de mar. de 2026, 15:57
+ 2 previous scans
Compatível com
Skill details
Updated semana passada
Analisado 31 de mar. de 2026, 15:57
Descricao
Process textual and multimedia files with various LLM providers using the llm CLI. Supports both non-interactive and interactive modes with model selection, config persistence, and file input handling.
Scans recentes
31 de mar. de 2026, 15:57
Latest analysis
31 de mar. de 2026, 15:12
Run 2
27 de mar. de 2026, 15:48
Run 1