SKILLEMALL.ai
GitHub ↗ RU Sign in

FC microsoft-365-graph-openclaw

Microsoft 365 Graph for OpenClaw with webhook-based wake signals. Reduce recurring LLM cost from inbox polling while managing Outlook mail, calendar, OneDrive, and contacts via Microsoft Graph.

Not recommendedlow grade F
ClawHub Agent Skills author: draeden79 v0.2.2 MIT-0 36 files · 4 scripts body ≈ 2 210 tokens Open the sourceclawhub.ai↗ analyzed 4 d ago

As a process C 63/100 · Has gaps — weak spots: result and completion, when it triggers, running it twice

IntegrationOutlookInfrastructurePersonal productivityAI and agentstype 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
F
32/100
safety, quality, tests
Safety 60%
10
Quality 40%
65
Run on models
none yet
Process rating
C
63/100
Has gaps
Result and completion w 14
0
When it triggers w 12
20
Running it twice w 4
30
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.

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

  1. Say in the description WHEN to use the skill ("use when…", example requests): that is the agent's main cue.
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 · 30

✓ No critical or high findings

Medium and low: 30
  • medium Dangerous commands cmd-privilege docs/minimal-setup.md:64
    Privilege escalation / world-writable permissions
    sudo bash scripts/run_mail_webhook_e2e_setup.sh \
  • medium Dangerous commands cmd-privilege docs/minimal-setup.md:77
    Privilege escalation / world-writable permissions
    sudo bash scripts/diagnose_mail_webhook_e2e.sh \
  • medium Dangerous commands cmd-privilege docs/minimal-setup.md:87
    Privilege escalation / world-writable permissions
    sudo bash scripts/run_mail_webhook_smoke_tests.sh \
  • medium Dangerous commands cmd-privilege README.md:115
    Privilege escalation / world-writable permissions
    sudo bash scripts/run_mail_webhook_e2e_setup.sh \
  • medium Dangerous commands cmd-privilege README.md:124
    Privilege escalation / world-writable permissions
    sudo bash scripts/diagnose_mail_webhook_e2e.sh \
  • medium Dangerous commands cmd-privilege README.md:131
    Privilege escalation / world-writable permissions
    sudo bash scripts/run_mail_webhook_smoke_tests.sh \
  • medium Dangerous commands cmd-privilege references/mail_webhook_adapter.md:55
    Privilege escalation / world-writable permissions
    sudo bash scripts/setup_mail_webhook_ec2.sh \
  • medium Dangerous commands cmd-privilege references/mail_webhook_adapter.md:75
    Privilege escalation / world-writable permissions
    sudo bash scripts/run_mail_webhook_e2e_setup.sh \
  • medium Dangerous commands cmd-privilege references/mail_webhook_adapter.md:86
    Privilege escalation / world-writable permissions
    sudo bash scripts/run_mail_webhook_e2e_setup.sh \
  • medium Dangerous commands cmd-privilege references/mail_webhook_adapter.md:102
    Privilege escalation / world-writable permissions
    sudo bash scripts/run_mail_webhook_smoke_tests.sh \
  • medium Dangerous commands cmd-privilege scripts/run_mail_webhook_e2e_setup.sh:15
    Privilege escalation / world-writable permissions
    sudo bash scripts/run_mail_webhook_e2e_setup.sh \
  • medium Dangerous commands cmd-privilege SKILL.md:129
    Privilege escalation / world-writable permissions
    sudo bash scripts/setup_mail_webhook_ec2.sh \
  • medium Dangerous commands cmd-privilege SKILL.md:140
    Privilege escalation / world-writable permissions
    sudo bash scripts/run_mail_webhook_e2e_setup.sh \
  • medium Dangerous commands cmd-privilege SKILL.md:151
    Privilege escalation / world-writable permissions
    sudo bash scripts/run_mail_webhook_e2e_setup.sh \
  • medium Dangerous commands cmd-privilege SKILL.md:163
    Privilege escalation / world-writable permissions
    sudo bash scripts/run_mail_webhook_smoke_tests.sh \
  • low Dangerous commands cmd-privilege docs/troubleshooting.md:13
    Privilege escalation / world-writable permissions (quoted — discussed, not commanded)
    4) Run `sudo bash scripts/diagnose_mail_webhook_e2e.sh --domain <your-domain> --repo-root "$(pwd)"` for full pipeline checks.
    quoted
  • low Dangerous commands cmd-privilege references/mail_webhook_adapter.md:123
    Privilege escalation / world-writable permissions (quoted — discussed, not commanded)
    - `sudo bash scripts/run_mail_webhook_smoke_tests.sh --domain ... --create-subscription --test-email ...`
    quoted
  • low Dangerous commands cmd-privilege scripts/run_mail_webhook_e2e_setup.sh:167
    Privilege escalation / world-writable permissions (string literal in code, not executed)
    echo "  sudo sh -lc 'ls -la /etc/openclaw /opt/openclaw ~/.openclaw ~/.config/openclaw 2>/dev/null'" >&2
    code literal
  • low Exfiltration exfil-secret-in-url scripts/run_mail_webhook_e2e_setup.sh:410
    Credential passed in a URL query string (normal for some APIs — verify the host is the intended service) (placeholder value)
    info "[DRY-RUN] GET https://$DOMAIN$ADAPTER_PATH?validationToken=…"
    placeholder
  • low Exfiltration exfil-secret-in-url scripts/run_mail_webhook_e2e_setup.sh:412
    Credential passed in a URL query string (normal for some APIs — verify the host is the intended service) (placeholder value)
    VALIDATION_URL="https://$DOMAIN$ADAPTER_PATH?validationToken=…"
    placeholder
  • low Exfiltration exfil-secret-in-url scripts/run_mail_webhook_smoke_tests.sh:111
    Credential passed in a URL query string (normal for some APIs — verify the host is the intended service) (placeholder value)
    LOCAL_RESULT="$(curl -fsS "http://127.0.0.1:${ADAPTER_PORT}${ADAPTER_PATH}?validationToken=…")"
    placeholder
  • low Exfiltration net-credential-use scripts/run_mail_webhook_smoke_tests.sh:111
    Credential used in a network call (verify the destination is the intended service) (test fixture / example file; quoted — discussed, not commanded)
    LOCAL_RESULT="$(curl -fsS "http://127.0.0.1:${ADAPTER_PORT}${ADAPTER_PATH}?validationToken=…")"
    fixturequoted
  • low Exfiltration exfil-secret-in-url scripts/run_mail_webhook_smoke_tests.sh:120
    Credential passed in a URL query string (normal for some APIs — verify the host is the intended service) (placeholder value)
    PUBLIC_RESULT="$(curl -fsS "https://${DOMAIN}${ADAPTER_PATH}?validationToken=…")"
    placeholder
  • low Exfiltration net-credential-use scripts/run_mail_webhook_smoke_tests.sh:120
    Credential used in a network call (verify the destination is the intended service) (destination host is a configured variable; test fixture / example file; quoted — discussed, not commanded)
    PUBLIC_RESULT="$(curl -fsS "https://${DOMAIN}${ADAPTER_PATH}?validationToken=…")"
    variable hostfixturequoted
  • low Dangerous commands cmd-background-process scripts/setup_mail_webhook_ec2.sh:251
    Starts a background / autostarted process
    run_cmd systemctl enable caddy
  • low Dangerous commands cmd-background-process scripts/setup_mail_webhook_ec2.sh:252
    Starts a background / autostarted process
    run_cmd systemctl enable --now graph-mail-webhook-adapter
  • low Dangerous commands cmd-background-process scripts/setup_mail_webhook_ec2.sh:253
    Starts a background / autostarted process
    run_cmd systemctl enable --now graph-mail-webhook-worker
  • low Dangerous commands cmd-background-process scripts/setup_mail_webhook_ec2.sh:254
    Starts a background / autostarted process
    run_cmd systemctl enable --now graph-mail-subscription-renew.timer
  • low Risky intent intent-offensive-security SKILL.md:123
    Offensive-security / dual-use content (legitimate for authorised testing; review intended use)
    - Default mode is `wake` (`/hooks/wake`, `mode=now`). Use `--hook-action agent` only when you explicitly need per-message rich payload delivery.

A further 1 matches are quotations in this security skill's documentation and are not counted as findings.

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

Against the Agent Skills spec

  • warning description-no-when description does not say WHEN to use the skill (no "use when")
  • note frontmatter-key unknown frontmatter key "homepage"
  • note frontmatter-key unknown frontmatter key "repository"
  • note frontmatter-key unknown frontmatter key "security"

Process rating: all ten parameters 63/100

  • 0Result and completion. Does not say what the result is
  • 20When it triggers. No condition that starts the skill
  • 30Running it twice. 18 mutating operations with no state check
  • 60Tools and files. Uses tools (bash, web, python) that frontmatter does not declare
  • 70Inputs and preconditions. Inputs and preconditions are listed
  • 100Steps. 72 steps
  • 100Failures and branches. 1 branches, has a failure section
  • 100Consistency. Name and required fields are in place
  • 100Execution cost. Instruction body is 2210 tokens
  • 100Progress reporting. Reports progress
  • low 10 top-level sections: this looks like several domains in one skill
  • low The response is described with custom markup (4 tags): a typed call is more reliable

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)
  • +3Output format is not stated: the model decides each time
  • -4Absolute local paths (C:\Users, /home/…): not portable
  • -2localhost URLs: will not work for another user
  • -32 of 14 scripts are never mentioned in SKILL.md
  • +2Single-language instructions
  • +3Description length 193: enough signal without eating the budget
  • +4Structure: 11 headings
  • +3Step-by-step instructions: 72 items
  • +4Has examples (10 code blocks)
  • +4Reference files are cited in the instructions (7 of 15)
  • +1License stated

Quality base 70; lint remarks subtract, signals add up to 100. Result: 65.

External checks

ClawHub: suspicious
The skill appears purpose-built for Microsoft 365 automation, but it asks for broad account access and has secret-handling and high-impact action guardrail gaps that warrant review before use.
LLM: suspicious (high) · VirusTotal: · 29 May 2026