ToolRouter Gateway
Repository: openclaw/skills
Author: neroagent · Source status: Clear source
Unified access to 150+ tools via ToolRouter API.
Score basis:Clear source · High risk signals · OpenClaw
Repository: pending
Author: byungkyu · Source status: Source needs review
Zoho Inventory API integration with managed OAuth.
Score basis:Source needs review · High risk signals · Claude
Trust level
74 · Review first
Usable, but inspect source, install method, and risk hints before adoption.
Risk decision
High attention
needs credentials, network access
Install readiness
instruction-only · source-link only
SkillTrust only shows install guidance and copy actions; it never executes installs.
Before you install
Review source, permissions, and execution risk first, then alternatives. Scores prioritize review; they do not replace manual judgment.
Review weakest dimensions and next actions before copying commands.
Public evidence is limited; avoid installing without extra review.
Audit grade
D · Limited evidence
Execution risk
Low
Evidence confidence
65%
SAS-v2.1 radar
SAS-v2.1
Audit grade
D · Limited evidence
Execution risk
Low
Top threats
identity privilege abuse, data exfiltration
Control gaps
missing repo, missing license
Evidence confidence
65%
Repository
Unavailable
Author
byungkyu
Community signal
3 stars · 0 forks
Last updated
2026-02-11
Primary source
Source needs review
Source status
Source needs review
Install method
instruction-only
Source & publisher integrity
11Focus: Who published it and whether it is traceable
Next action: Review repository, author, and README first; do not install directly when source is pending.
High-risk action confirmation
38Focus: Whether destructive or external actions require confirmation
Next action: Avoid directly installing high-risk skills without confirmation controls.
Secrets, identity & credentials
42Focus: Whether it handles tokens, private keys, or agent identity
Next action: Do not provide long-lived tokens or private keys to source-pending skills.
Supported tools can change install steps; Universal entries need source review.
Explicitly supported
Candidate support (inferred)
Candidate tools are inferred signals, not official compatibility certifications.
No explicit install command yet. Review source and install docs before deciding.Copy is disabled because no explicit command is available yet.
needs credentials, network access
Review source and permissions before copying install commands.
Public evidence is limited; avoid installing without extra review.
Focus: Who published it and whether it is traceable
Next action: Review repository, author, and README first; do not install directly when source is pending.
Focus: Whether install steps can be reviewed
Next action: Prefer candidates with install docs and repository evidence.
Focus: Whether tool descriptions may hide instructions
Next action: Read README, rules, and tool descriptions before install.
Focus: What it can access
Next action: Grant only task-required permissions and prefer Ask/manual confirmation.
Focus: Whether it runs commands or scripts
Next action: Manually confirm command-running skills in an isolated directory.
Focus: Whether file reads/writes can escape scope
Next action: Check working directory and file access scope before running.
Focus: Whether it may send data out
Next action: If unsure, restrict network access or allow only known domains.
Focus: Whether it handles tokens, private keys, or agent identity
Next action: Do not provide long-lived tokens or private keys to source-pending skills.
Focus: Whether external content can steer behavior
Next action: For browser/RAG/rules skills, review permissions and confirmation controls first.
Focus: Whether memory or retrieved context can be poisoned
Next action: Try RAG/memory skills in a low-privilege environment first.
Focus: Whether external tools and MCP access are clearly bounded
Next action: Confirm which external tools it will connect to before install, and start with the smallest possible set.
Focus: Whether destructive or external actions require confirmation
Next action: Avoid directly installing high-risk skills without confirmation controls.
Focus: How far impact can spread when something goes wrong
Next action: If unsure, test in an isolated project first.
Focus: Whether actions can be traced
Next action: Prefer candidates with logs or previews.
Focus: Whether it is maintained and reusable
Next action: Check license and maintenance before organizational use.
Usable, but inspect source, install method, and risk hints before adoption.
Phase 1 only shows installation-aware, source-backed signals. SkillTrust does not execute install scripts for users.
Risk factors
needs credentials, network access
Permission hints
review skill metadata before install, check required credentials in skill docs
Why related: Same task category, Also supports Open Claw...
Why related: Same task category, Also supports Open Claw, Keyword overlap
Repository: openclaw/skills
Author: byungkyu · Source status: Clear source
Vercel API integration with managed OAuth.
Score basis:Clear source · High risk signals · Cursor
Why related: Also supports Cursor, Keyword overlap...
Why related: Also supports Cursor, Keyword overlap, Same author
Repository: openclaw/skills
Author: neroagent · Source status: Clear source
Automated audit and fix for OpenClaw agent harnesses.
Score basis:Clear source · High risk signals · Claude
Why related: Same task category, Also supports Open Claw, Claude...
Why related: Same task category, Also supports Open Claw, Claude, Keyword overlap
Repository: openclaw/skills
Author: twinsgeeks · Source status: Clear source
Chemistry between AI agents — find chemistry through personality matching, chemistry scoring, and chemistry-driven connections.
Score basis:Clear source · High risk signals · Claude
Why related: Same task category, Also supports Open Claw, Claude...
Why related: Same task category, Also supports Open Claw, Claude, Keyword overlap
Repository: openclaw/skills
Author: twinsgeeks · Source status: Clear source
Icebreaker prompts for AI agents — break the ice with personality-matched agents, icebreaker conversations, and icebreaker openers that actually work.
Score basis:Clear source · High risk signals · Claude
Why related: Same task category, Also supports Open Claw, Claude...
Why related: Same task category, Also supports Open Claw, Claude, Keyword overlap
Repository: openclaw/skills
Author: ts-sz · Source status: Clear source
Connect your AI agent to 1000+ apps — discover tools, manage OAuth connections, execute actions, and provide a self-service connector dashboard.
Score basis:Clear source · High risk signals · Universal
Why related: Same task category, Keyword overlap
Why related: Same task category, Keyword overlap
Repository: openclaw/skills
Author: byungkyu · Source status: Clear source
Vercel API integration with managed OAuth.
Score basis:Clear source · High risk signals · Cursor
Repository: pending
Author: byungkyu · Source status: Source needs review
Connect to 100+ APIs (Google Workspace, Microsoft 365, GitHub, Notion, Slack, Airtable, HubSpot, etc.) with managed OAuth.
Score basis:Source needs review · High risk signals · Claude
Repository: pending
Author: byungkyu · Source status: Source needs review
LinkedIn API integration with managed OAuth.
Score basis:Source needs review · High risk signals · Claude