Phantom Limb

Detects phantom dependencies — references to things that no longer exist, ghost state that lives in the gaps between modules, and invisible wires that connec...

This skill is coherent for repository/static analysis and does not request extra credentials or install software, but it will scan source code, .env files, CI/CD configs, and deployment manifests — files that often contain secrets. Before installing or running it: (1) restrict which repositories/paths the agent can access, (2) avoid scanning production credential stores or highly sensitive manifests, (3) run initially on a copy of the repo or a subset to see what it reports, and (4) confirm whether the skill will fetch external API schemas (and whether those lookups require authentication). If you need stricter guarantees, ask the skill author to document exact file/path whitelists and any outgoing network endpoints used during analysis.

Type: OpenClaw Skill Name: phantom-limb Version: 1.0.0 The 'phantom-limb' skill is a static analysis tool designed to detect 'phantom dependencies' in codebases. The `SKILL.md` clearly outlines its diagnostic purpose, detailing methods like scanning source files, environment variables, and configuration files (e.g., `.env`, CI/CD configs, deployment manifests). Crucially, it explicitly states 'Zero external dependencies. Zero API calls' and `requires_api: false`, indicating no intent for data exfiltration or unauthorized network communication. There is no evidence of malicious instructions, obfuscation, or attempts to manipulate the AI agent for harmful purposes; all described actions are consistent with its stated code health diagnostic function.