Firm Config Migration Pack
v1.0.0Configuration migration and integrity audit pack. Shell env sanitization, plugin integrity, token separation, OTEL redaction, and RPC rate limiting. 5 migrat...
⭐ 0· 279·1 current·1 all-time
MIT-0
Download zip
LicenseMIT-0 · Free to use, modify, and redistribute. No attribution required.
Security Scan
OpenClaw
Suspicious
medium confidencePurpose & Capability
The name and description (config migration, env sanitization, plugin integrity, OTEL redaction, RPC rate-limiting) line up with the listed checks. The SKILL.md declares a dependency on mcp-openclaw-extensions >= 3.0.0 which plausibly provides the five named tools. However, the skill does not include the tools, binaries, or an install spec itself; it assumes an external extension is present. That dependency is reasonable but deserves verification (who publishes mcp-openclaw-extensions?).
Instruction Scope
The runtime instructions are short and scoped: examples call tools with a config_path argument (e.g., openclaw_shell_env_check config_path=/path/to/config.json). They do not explicitly instruct reading unrelated system files or contacting external endpoints. However, the checks (shell env sanitization, token separation, OTEL PII redaction) necessarily inspect environment variables and configuration files which can contain secrets or PII. Because the skill is instruction-only and delegates behavior to external tools, the precise actions depend entirely on those tools' implementations — which are not provided here.
Install Mechanism
No install spec and no code files (instruction-only) — lowest risk in terms of code being written by the skill itself. But the SKILL.md declares mcp-openclaw-extensions >= 3.0.0 as a required dependency without giving a source or install method. This means the agent must already have that extension or fetch it from elsewhere; the lack of provenance for that dependency is a concern and should be validated before use.
Credentials
The skill declares no required environment variables, yet several checks imply access to environment variables (LD_PRELOAD/DYLD_*, tokens, OTEL data) and to configuration files. Inspecting env/config is reasonable for its purpose, but those are sensitive data sources. The SKILL.md does not enumerate what environment or secrets it will read, nor how data is handled or whether external reporting occurs. That mismatch (no declared env access but implied sensitive reads) justifies caution.
Persistence & Privilege
always is false and there is no install that writes persistent agent-wide configuration. The skill does not request permanent presence or attempt to modify other skills' configs. Autonomous invocation is allowed (default) but that is normal and not a standalone concern here.
What to consider before installing
This skill appears to describe legitimate configuration and integrity checks, but it is instruction-only and depends on an external extension (mcp-openclaw-extensions) that is not included or linked. Before installing or running: 1) Verify the source and publisher of mcp-openclaw-extensions and obtain its code or package from a trusted place; 2) Inspect the implementations of the named tools (openclaw_shell_env_check, openclaw_plugin_integrity_check, etc.) to confirm they only read the expected config/env paths and do not exfiltrate data; 3) Run the checks in a restricted/sandbox environment first and review logs/output for unexpected network activity; 4) Because the SKILL.md warns 'generated by AI — human validation required', perform a manual review of the logic, and ensure no secrets or tokens are transmitted to external endpoints; 5) If you cannot verify the dependency provenance or tool implementations, do not enable this skill in production environments.Like a lobster shell, security has layers — review code before you run it.
latestvk974ez2gr7z7t1717v374ymdg982538z
License
MIT-0
Free to use, modify, and redistribute. No attribution required.