FD tool-connector

Connect OpenClaw to tools like Slack, GitHub, Jira, Confluence, Grafana, Datadog, PagerDuty, Outlook, and Google Drive with minimal input — just paste a URL and the skill figures out the rest. Everything stays local; no credentials or data leave your machine. Uses your own identity (no OAuth apps, no IT tickets). Also teaches how to add brand-new tool connections from scratch (10xProductivity methodology). Use when the user wants to connect to a tool, set up credentials, access a service API, add a new integration, or ask "how do I give my agent access to X". CAUTION: SSO tools use Python Playwright browser automation to capture session tokens from a headed Chromium window; credentials are stored in ~/.openclaw/openclaw.json under skills.entries.tool-connector only. Review scripts/playwright_sso.py and scripts/openclaw_sync.py before use.

Not recommendedlow grade F

ClawHub Agent Skills author: ZhixiangLuo v1.0.2 MIT-0 36 files body ≈ 1 578 tokens Open the sourceclawhub.ai↗ analyzed 3 d ago

As a process D 49/100 · Unfinished process — weak spots: result and completion, inputs and preconditions, failures and branches

Procedure Playwright GitHub Google Drive Confluence Infrastructure AI and agents Software developmenttype and topics are labelled automatically from the skill text

Runs in: OpenClaw Claude / Claude Code ChatGPT / Codex Gemini CLI Cursor GitHub Copilot / VS Code Qwen Code Kimi Code CLI Z.ai (GLM) DeepSeek (Deep Code) Mistral Vibe LangChain (deepagents) Goose OpenCode

JSON

Technical rating

31/100

safety, quality, tests

Safety 60%: 0
Quality 40%: 78
Run on models: none yet

Process rating

49/100

Unfinished process

Result and completion w 14: 0
Inputs and preconditions w 11: 0
Failures and branches w 10: 0

the three weakest of ten parameters · all ten

What is at stake

Medium-severity findings: the skill is probably honest, but read what alarmed the scanner.

Exfiltration medium severity

Below is the worst case for this category. The finding here is medium: the guard saw a sign, not a proof.

If you install

The instructions or scripts send data out: environment variables, keys, file contents, chat history. You may never notice, because the agent performs the upload as "part of the task".

For the author

If the upload is not needed for the task, remove it: catalogs flag such skills and delist them. If it is needed, name the destination explicitly, say what leaves the machine, and give the user a switch.

Dangerous commands medium severity

Below is the worst case for this category. The finding here is medium: the guard saw a sign, not a proof.

If you install

The skill contains commands that delete files, rewrite disks or execute code fetched from the network. The agent may run them without asking if it believes the instructions require it.

For the author

Replace destructive commands with safe equivalents that ask for confirmation, scope them to one folder, and stop piping curl into a shell: pin a version and a checksum.

How to improve

For the model run — optional

Your own cases (evals/evals.json, 4–6 real requests with expected answers): the full check would then run those instead of a model-drafted suite.
A spec.yaml with trigger phrases and assertions — a behaviour contract for CI; `skilltest init` writes a template.

Guard findings · 77

✓ No critical or high findings

Medium and low: 77

medium Exfiltration net-credential-use references/add-new-tool.md:150

Credential used in a network call (verify the destination is the intended service)
```
curl -s "$TOOL_BASE_URL/users/me" -H "Authorization: Bearer $TOOL_API_TOKEN" | jq .
```
medium Exfiltration net-credential-use references/add-new-tool.md:153

Credential used in a network call (verify the destination is the intended service)
```
curl -s "$TOOL_BASE_URL/items?limit=5" -H "Authorization: Bearer $TOOL_API_TOKEN" | jq .
```
medium Exfiltration net-credential-use references/add-new-tool.md:241

Credential used in a network call (verify the destination is the intended service)
```
curl -s "$BASE/endpoint" -H "Authorization: Bearer $TOOL_API_TOKEN" | jq .
```
medium Exfiltration net-credential-use references/tool_connections/bitbucket-server/connection-api-token.md:52

Credential used in a network call (verify the destination is the intended service)
```
curl -s -k -H "Authorization: Bearer $BITBUCKET_TOKEN" \
```
medium Exfiltration net-credential-use references/tool_connections/bitbucket-server/connection-api-token.md:68

Credential used in a network call (verify the destination is the intended service)
```
curl -s -k -H "Authorization: Bearer $BITBUCKET_TOKEN" \
```
medium Exfiltration net-credential-use references/tool_connections/bitbucket-server/connection-api-token.md:74

Credential used in a network call (verify the destination is the intended service)
```
curl -s -k -H "Authorization: Bearer $BITBUCKET_TOKEN" \
```
medium Exfiltration net-credential-use references/tool_connections/bitbucket-server/connection-api-token.md:80

Credential used in a network call (verify the destination is the intended service)
```
curl -s -k -H "Authorization: Bearer $BITBUCKET_TOKEN" \
```
medium Exfiltration net-credential-use references/tool_connections/bitbucket-server/connection-api-token.md:86

Credential used in a network call (verify the destination is the intended service)
```
curl -s -k -H "Authorization: Bearer $BITBUCKET_TOKEN" \
```
medium Exfiltration net-credential-use references/tool_connections/bitbucket-server/setup.md:39

Credential used in a network call (verify the destination is the intended service)
```
curl -s -k -H "Authorization: Bearer $BITBUCKET_TOKEN" \
```
medium Exfiltration net-credential-use references/tool_connections/confluence/connection-api-token.md:36

Credential used in a network call (verify the destination is the intended service)
```
curl -s -u "$CONFLUENCE_EMAIL:$CONFLUENCE_TOKEN" \
```
medium Exfiltration net-credential-use references/tool_connections/confluence/connection-api-token.md:42

Credential used in a network call (verify the destination is the intended service)
```
# curl -s -H "Authorization: Bearer $CONFLUENCE_TOKEN" \
```
medium Exfiltration net-credential-use references/tool_connections/confluence/connection-api-token.md:57

Credential used in a network call (verify the destination is the intended service)
```
curl -s -u "$CONFLUENCE_EMAIL:$CONFLUENCE_TOKEN" \
```
medium Exfiltration net-credential-use references/tool_connections/confluence/connection-api-token.md:62

Credential used in a network call (verify the destination is the intended service)
```
curl -s -u "$CONFLUENCE_EMAIL:$CONFLUENCE_TOKEN" \
```
medium Exfiltration net-credential-use references/tool_connections/confluence/connection-api-token.md:67

Credential used in a network call (verify the destination is the intended service)
```
curl -s -u "$CONFLUENCE_EMAIL:$CONFLUENCE_TOKEN" \
```
medium Exfiltration net-credential-use references/tool_connections/confluence/setup.md:38

Credential used in a network call (verify the destination is the intended service)
```
curl -s -u "$CONFLUENCE_EMAIL:$CONFLUENCE_TOKEN" \
```
medium Exfiltration net-credential-use references/tool_connections/confluence/setup.md:63

Credential used in a network call (verify the destination is the intended service)
```
curl -s -H "Authorization: Bearer $CONFLUENCE_TOKEN" \
```
medium Exfiltration net-credential-use references/tool_connections/github/connection-api-token.md:30

Credential used in a network call (verify the destination is the intended service)
```
curl -s -H "Authorization: token $GITHUB_TOKEN" \
```
medium Exfiltration net-credential-use references/tool_connections/github/connection-api-token.md:45

Credential used in a network call (verify the destination is the intended service)
```
curl -s -H "Authorization: token $GITHUB_TOKEN" \
```
medium Exfiltration net-credential-use references/tool_connections/github/connection-api-token.md:50

Credential used in a network call (verify the destination is the intended service)
```
curl -s -H "Authorization: token $GITHUB_TOKEN" \
```
medium Exfiltration net-credential-use references/tool_connections/github/connection-api-token.md:55

Credential used in a network call (verify the destination is the intended service)
```
curl -s -H "Authorization: token $GITHUB_TOKEN" \
```
medium Exfiltration net-credential-use references/tool_connections/github/connection-api-token.md:60

Credential used in a network call (verify the destination is the intended service)
```
curl -s -H "Authorization: token $GITHUB_TOKEN" \
```
medium Exfiltration net-credential-use references/tool_connections/github/setup.md:31

Credential used in a network call (verify the destination is the intended service)
```
curl -s -H "Authorization: token $GITHUB_TOKEN" \
```
medium Exfiltration net-credential-use references/tool_connections/jenkins/connection-api-token.md:56

Credential used in a network call (verify the destination is the intended service)
```
curl -s -u "$JENKINS_USER:$JENKINS_TOKEN" \
```
medium Exfiltration net-credential-use references/tool_connections/jenkins/connection-api-token.md:73

Credential used in a network call (verify the destination is the intended service)
```
curl -s -u "$JENKINS_USER:$JENKINS_TOKEN" \
```
medium Exfiltration net-credential-use references/tool_connections/jenkins/connection-api-token.md:79

Credential used in a network call (verify the destination is the intended service)
```
curl -s -u "$JENKINS_USER:$JENKINS_TOKEN" \
```
medium Exfiltration net-credential-use references/tool_connections/jenkins/connection-api-token.md:86

Credential used in a network call (verify the destination is the intended service)
```
curl -s -u "$JENKINS_USER:$JENKINS_TOKEN" \
```
medium Exfiltration net-credential-use references/tool_connections/jenkins/connection-api-token.md:92

Credential used in a network call (verify the destination is the intended service)
```
curl -s -u "$JENKINS_USER:$JENKINS_TOKEN" \
```
medium Exfiltration net-credential-use references/tool_connections/jenkins/setup.md:38

Credential used in a network call (verify the destination is the intended service)
```
curl -s -u "$JENKINS_USER:$JENKINS_TOKEN" \
```
medium Dangerous commands cmd-eval-dynamic scripts/shared_utils/browser.py:22

Dynamic code execution from decoded/untrusted input
```
os.system(f"{sys.executable} -m pip install playwright -q")
```
medium Dangerous commands cmd-eval-dynamic scripts/shared_utils/browser.py:23

Dynamic code execution from decoded/untrusted input
```
os.system(f"{sys.executable} -m playwright install chromium -q")
```
medium Dangerous commands cmd-eval-dynamic scripts/shared_utils/playwright_sso.py:57

Dynamic code execution from decoded/untrusted input
```
os.system(f"{sys.executable} -m pip install playwright -q")
```
medium Dangerous commands cmd-eval-dynamic scripts/shared_utils/playwright_sso.py:58

Dynamic code execution from decoded/untrusted input
```
os.system(f"{sys.executable} -m playwright install chromium -q")
```
low Exfiltration read-dotenv references/add-new-tool.md:133

Reads a .env file
```
source .env
```
low Exfiltration read-dotenv references/add-new-tool.md:226

Reads a .env file
```
source .env
```
low Exfiltration read-dotenv references/add-new-tool.md:237

Reads a .env file
```
source .env
```
low Exfiltration read-dotenv references/tool_connections/artifactory/connection-api-token.md:40

Reads a .env file
```
source .env
```
low Exfiltration read-dotenv references/tool_connections/artifactory/connection-api-token.md:50

Reads a .env file
```
source .env
```
low Exfiltration read-dotenv references/tool_connections/artifactory/connection-api-token.md:64

Reads a .env file
```
source .env
```
low Exfiltration read-dotenv references/tool_connections/artifactory/setup.md:39

Reads a .env file
```
source .env
```
low Exfiltration read-dotenv references/tool_connections/backstage/connection-api-token.md:42

Reads a .env file
```
source .env
```
low Exfiltration read-dotenv references/tool_connections/backstage/connection-api-token.md:60

Reads a .env file
```
source .env
```
low Exfiltration read-dotenv references/tool_connections/backstage/connection-api-token.md:74

Reads a .env file
```
source .env
```
low Exfiltration read-dotenv references/tool_connections/backstage/setup.md:43

Reads a .env file
```
source .env
```
low Exfiltration read-dotenv references/tool_connections/bitbucket-server/connection-api-token.md:39

Reads a .env file
```
source .env
```
low Exfiltration read-dotenv references/tool_connections/bitbucket-server/connection-api-token.md:49

Reads a .env file
```
source .env
```
low Exfiltration read-dotenv references/tool_connections/bitbucket-server/connection-api-token.md:64

Reads a .env file
```
source .env
```
low Exfiltration read-dotenv references/tool_connections/bitbucket-server/setup.md:38

Reads a .env file
```
source .env
```
low Exfiltration read-dotenv references/tool_connections/confluence/connection-api-token.md:33

Reads a .env file
```
source .env
```
low Exfiltration read-dotenv references/tool_connections/confluence/connection-api-token.md:54

Reads a .env file
```
source .env
```
low Exfiltration read-dotenv references/tool_connections/confluence/connection-api-token.md:82

Reads a .env file
```
source .env
```
low Exfiltration read-dotenv references/tool_connections/confluence/connection-api-token.md:105

Reads a .env file
```
source .env
```
low Exfiltration read-dotenv references/tool_connections/confluence/setup.md:37

Reads a .env file
```
source .env
```
low Exfiltration read-dotenv references/tool_connections/confluence/setup.md:62

Reads a .env file
```
source .env
```
low Exfiltration read-dotenv references/tool_connections/datadog/connection-api-key.md:41

Reads a .env file
```
source .env
```
low Exfiltration read-dotenv references/tool_connections/datadog/connection-api-key.md:53

Reads a .env file
```
source .env
```
low Exfiltration read-dotenv references/tool_connections/datadog/setup.md:43

Reads a .env file
```
source .env
```
low Exfiltration read-dotenv references/tool_connections/github/connection-api-token.md:29

Reads a .env file
```
source .env
```
low Exfiltration read-dotenv references/tool_connections/github/connection-api-token.md:42

Reads a .env file
```
source .env
```
low Exfiltration read-dotenv references/tool_connections/github/connection-api-token.md:75

Reads a .env file
```
source .env
```
low Exfiltration read-dotenv references/tool_connections/github/connection-api-token.md:93

Reads a .env file
```
source .env
```

…and 17 more

Files scanned: 36. Evidence is masked. Grey chips explain why severity was lowered.

Against the Agent Skills spec

warning frontmatter-yaml SKILL.md: the frontmatter is not valid YAML (YAML parse error: Nested mappings are not allowed in compact mappings at line 2, column 14: description: Connect OpenClaw to tools like Slack, GitHub, Jira, Confluence, Gr… ^ ); fields were read line by line. The usual cause is a colon inside an unquoted value

Process rating: all ten parameters 49/100

0Result and completion. Does not say what the result is
0Inputs and preconditions. Does not say what the process needs to start
0Failures and branches. Linear process with no failure handling
0Progress reporting. Says nothing while it works
30Running it twice. 1 mutating operations with no state check
60Tools and files. Uses tools (python) that frontmatter does not declare
70When it triggers. States when to use, but not when not to
100Steps. 5 steps
100Consistency. Name and required fields are in place
100Execution cost. Instruction body is 1578 tokens

Everything here is measured from the skill text rather than judged by a model, so the numbers are checkable. A parameter weighs more when it is a more common reason for the process to stall.

Quality signals

+5Description has no quoted example phrases that should trigger the skill
+4Description does not say when NOT to use the skill (false activations)
+3Description length 850: 120–800 characters recommended
+3Output format is not stated: the model decides each time
+1No license
+2Single-language instructions
+4Structure: 5 headings
+3Step-by-step instructions: 5 items
+4Has examples (2 code blocks)
+4Reference files are cited in the instructions (2 of 2)
+3All 1 scripts are documented

Quality base 70; lint remarks subtract, signals add up to 100. Result: 78.

External checks

ClawHub: suspicious

The skill is transparent about connecting tools, but it captures and persists browser/session credentials for many services and weakens transport security checks, so it needs careful review before installation.

LLM: suspicious (high) · VirusTotal: · 29 May 2026

Tests

— no evals.json

— no spec.yaml

— not run on models

Files · 36

references/add-new-tool.md 12K
references/setup.md 11K
references/tool_connections/artifactory/connection-api-token.md 5K
references/tool_connections/artifactory/setup.md 2K
references/tool_connections/backstage/connection-api-token.md 6K
references/tool_connections/backstage/setup.md 2K
references/tool_connections/bitbucket-server/connection-api-token.md 6K
references/tool_connections/bitbucket-server/setup.md 2K
references/tool_connections/confluence/connection-api-token.md 5K
references/tool_connections/confluence/setup.md 3K
references/tool_connections/datadog/connection-api-key.md 6K
references/tool_connections/datadog/setup.md 2K
references/tool_connections/github/connection-api-token.md 5K
references/tool_connections/github/setup.md 2K
references/tool_connections/google-drive/connection-browser-session.md 10K
references/tool_connections/google-drive/setup.md 2K
references/tool_connections/grafana/connection-sso.md 4K
references/tool_connections/grafana/setup.md 2K
references/tool_connections/jenkins/connection-api-token.md 6K
references/tool_connections/jenkins/setup.md 2K
references/tool_connections/jira/connection-api-token.md 7K
references/tool_connections/jira/setup.md 2K
references/tool_connections/microsoft-teams/connection-personal-sso.md 7K
references/tool_connections/microsoft-teams/setup.md 2K
references/tool_connections/outlook/connection-m365.md 9K
references/tool_connections/outlook/connection-personal.md 6K
references/tool_connections/outlook/setup.md 4K
references/tool_connections/pagerduty/connection-api-token.md 7K
references/tool_connections/pagerduty/setup.md 1K
references/tool_connections/slack/connection-sso.md 11K
references/tool_connections/slack/setup.md 2K
scripts/openclaw_sync.py 6K
scripts/shared_utils/browser.py 5K
scripts/shared_utils/playwright_sso.py 34K
skill-card.md 3K
SKILL.md 10K

Dates

In catalog since 20 Mar 2026

Updated in catalog 18 May 2026

First seen here 10 Sept 2026

Last analysis 11 Sept 2026, 02:28 UTC

Last seen in crawl 6 h ago

Score history

Date		Score	Safety	Qual.
11 Sept 2026	F	31	0	78
10 Sept 2026	F	0	0	0