SKILLEMALL.ai
GitHub ↗ RU Sign in

DD google-gmail

Read, search, triage, label, archive and send Gmail mail / threads / labels / attachments via the Gmail v1 REST API. Use when the user mentions Gmail, "my inbox", unread mail, recent emails from someone, summarising a thread, downloading an attachment, finding mail by label / query, archiving or labelling a thread, or drafting and sending a reply / new message.

AceDataCloud/Skills Agent Skills author: AceDataCloud 1 file body ≈ 4 210 tokens Open the sourcegithub.com↗ analyzed 5 h ago

Read, search, triage, label, archive and send Gmail mail / threads / labels / attachments via the Gmail v1 REST API.

As a process D 48/100 · Unfinished process — weak spots: steps, result and completion, inputs and preconditions

IntegrationGmailMarketingSoftware developmentWriting and documentstype and topics are labelled automatically from the skill text
Runs in: 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) OpenClaw Goose OpenCode
JSON
Technical rating
D
77/100
safety, quality, tests
Safety 60%
75
Quality 40%
80
Run on models
none yet
Process rating
D
48/100
Unfinished process
Steps w 15
0
Result and completion w 14
0
Inputs and preconditions w 11
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.

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.

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 · 5

    ✓ No critical or high findings

    Medium and low: 5
    • medium Exfiltration net-credential-use SKILL.md:123
      Credential used in a network call (verify the destination is the intended service)
      curl -sS -H "Authorization: Bearer $GOOGLE_GMAIL_TOKEN" \
    • medium Exfiltration net-credential-use SKILL.md:131
      Credential used in a network call (verify the destination is the intended service)
      curl -sS -H "Authorization: Bearer $GOOGLE_GMAIL_TOKEN" \
    • medium Exfiltration net-credential-use SKILL.md:154
      Credential used in a network call (verify the destination is the intended service)
      IDS=$(curl -sS -H "Authorization: Bearer $GOOGLE_GMAIL_TOKEN" \
    • medium Exfiltration net-credential-use SKILL.md:163
      Credential used in a network call (verify the destination is the intended service)
      curl -sS -H "Authorization: Bearer $GOOGLE_GMAIL_TOKEN" \
    • medium Exfiltration net-credential-use SKILL.md:177
      Credential used in a network call (verify the destination is the intended service)
      RESP=$(curl -sS -H "Authorization: Bearer $GOOGLE_GMAIL_TOKEN" \

    Files scanned: 1. Evidence is masked. Grey chips explain why severity was lowered.

    Against the Agent Skills spec

    • note frontmatter-key unknown frontmatter key "connections"
    • note frontmatter-key unknown frontmatter key "allowed_tools"

    Process rating: all ten parameters 48/100

    • 0Steps. Prose only: no discrete steps
    • 0Result and completion. Does not say what the result is
    • 30Inputs and preconditions. Does not say what the process needs to start
    • 30Running it twice. 21 mutating operations with no state check
    • 60Tools and files. Uses tools (bash, web) that frontmatter does not declare
    • 70When it triggers. States when to use, but not when not to
    • 70Execution cost. Instruction body is 4210 tokens
    • 100Failures and branches. 4 branches, has a failure section
    • 100Consistency. Name and required fields are in place
    • 100Progress reporting. Reports progress
    • medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing

    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)
    • +3No numbered steps or checklist
    • +3Output format is not stated: the model decides each time
    • +2Single-language instructions
    • +3Description length 363: enough signal without eating the budget
    • +4Structure: 23 headings
    • +4Has examples (21 code blocks)
    • +1License stated

    Quality base 70; lint remarks subtract, signals add up to 100. Result: 80.