Skill flagged — suspicious patterns detected
ClawHub Security flagged this skill as suspicious. Review the scan results before using.
Architecture Decision Records
v1.0.0Document significant technical decisions with context, rationale, and consequences to maintain clear, lightweight architectural records for future reference.
⭐ 0· 1.1k·8 current·10 all-time
by@wpank
MIT-0
Download zip
LicenseMIT-0 · Free to use, modify, and redistribute. No attribution required.
Security Scan
OpenClaw
Benign
high confidencePurpose & Capability
The skill's name (Architecture Decision Records) matches the content: templates, lifecycle, and guidance for ADRs. There are no unexpected required binaries, env vars, or config paths.
Instruction Scope
SKILL.md contains templates, guidelines, and example ADRs only. It does not instruct the agent to read arbitrary user files, access secrets, or exfiltrate data. The README contains installation/copy examples for local skill directories, but those are user-facing instructions rather than runtime commands the agent will execute.
Install Mechanism
There is no install spec in the registry (instruction-only), which is low-risk. The README suggests installation via an npx add pointing at a GitHub path and copying from ~/.ai-skills into ~/.cursor/.claude — these are manual actions. If you plan to follow the README, prefer installing from a verified repository or review the repo contents before running npx or copying files from another user's home directory.
Credentials
The skill declares no environment variables, credentials, or config paths. Nothing requested is disproportionate to an ADR documentation purpose.
Persistence & Privilege
The skill does not request always:true and is user-invocable. It does not instruct modifying other skills or global agent settings. Default autonomous invocation remains allowed (platform default).
Assessment
This skill is a documentation/template pack for Architecture Decision Records and appears internally consistent. Before installing or running any commands from the README: 1) inspect the GitHub repository referenced by the npx example (or avoid npx and fetch a release you trust); 2) do not blindly run npx or scripts from unknown sources; 3) copying files into ~/.cursor, ~/.claude, or ~/.ai-skills will create files in your home directory—review what will be written and the file contents/permissions first. No credentials or system access are required by the skill itself.Like a lobster shell, security has layers — review code before you run it.
latestvk9769hegcgxpdfa3dmjgnbcf0x80w8sb
License
MIT-0
Free to use, modify, and redistribute. No attribution required.