Trusted — Risk Score 0/100
Last scan:1 day ago Rescan
0 /100
lobster-fork-mode
Fork子Agent模式 — 子Agent继承父上下文
Pure documentation skill describing a subagent fork pattern with no executable code or sensitive operations.
Skill Namelobster-fork-mode
Duration16.4s
Enginepi
Safe to install
No action required. This is a benign documentation file.
ResourceDeclaredInferredStatusEvidence
Filesystem NONE NONE N/A - documentation only
Network NONE NONE N/A - no network code
Shell NONE NONE N/A - no shell execution
Environment NONE NONE N/A - no env access
Skill Invoke sessions_spawn sessions_spawn ✓ Aligned SKILL.md:1 - declared in metadata
Clipboard NONE NONE N/A - no clipboard access
Browser NONE NONE N/A - no browser operations
Database NONE NONE N/A - no database access

File Tree

1 files · 2.2 KB · 79 lines
Markdown 1f · 79L
└─ 📝 SKILL.md Markdown 79L · 2.2 KB

Security Positives

✓ Documentation-only skill with no executable code
✓ No external dependencies or package files
✓ Declared metadata (sessions_spawn, read, memory_search) is consistent with described functionality
✓ No obfuscation, credential harvesting, or data exfiltration patterns
✓ No remote script execution or base64-encoded payloads
✓ No sensitive file path access (.ssh, .aws, .env)