SKILLEMALL.ai
GitHub ↗ RU Sign in

CC secrets

Declaratively register API keys and service credentials a template needs so they appear on Settings › API keys and in the onboarding checklist. Use before adding any third-party credential or setup UI so API keys, OAuth connections, and scoped configuration use the correct shared primitive.

BuilderIO/agent-native Agent Skills author: BuilderIO 1 file body ≈ 5 050 tokens Open the sourcegithub.com↗ analyzed 3 d ago

Declaratively register API keys and service credentials a template needs so they appear on Settings › API keys and in the onboarding checklist.

As a process C 64/100 · Has gaps — weak spots: result and completion, when it triggers

IntegrationSlackSecuritytype 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
C
83/100
safety, quality, tests
Safety 60%
89
Quality 40%
73
Run on models
none yet
Process rating
C
64/100
Has gaps
Result and completion w 14
0
When it triggers w 12
20
Tools and files w 18
60
the three weakest of ten parameters · all ten

The same skill appears in 8 more places: agent-native, agent-native, agent-native, agent-native, agent-native, agent-native, agent-native, agent-native

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

  1. The SKILL.md body is over 5,000 tokens: move reference detail into references/ and load it when needed.
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 · 3

✓ No critical or high findings

Medium and low: 3
  • medium Exfiltration exfil-webhook-url SKILL.md:366
    Webhook / callback URL commonly used for exfiltration (verify the destination) (quoted — discussed, not commanded)
    "urlAllowlist": ["https://hooks.slack.com"]
    quoted
  • medium Exfiltration exfil-webhook-url SKILL.md:392
    Webhook / callback URL commonly used for exfiltration (verify the destination) (quoted — discussed, not commanded)
    ["https://hooks.slack.com"],
    quoted
  • low Exfiltration exfil-webhook-url SKILL.md:391
    Webhook / callback URL commonly used for exfiltration (verify the destination) (placeholder value)
    "https://hooks.slack.com/services/<WORKSPACE>/<CHANNEL>/<SECRET>",
    placeholder

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

Against the Agent Skills spec

  • warning body-long SKILL.md body ≈ 5050 tokens (recommended < 5000); move details to references/
  • note frontmatter-key unknown frontmatter key "scope"
  • note edit-residue the text marks something as outdated (lines 13, 309, 311, 312, 407): check that old rules are not kept next to new ones — the full check reads the text for contradictions

Process rating: all ten parameters 64/100

  • 0Result and completion. Does not say what the result is
  • 20When it triggers. No condition that starts the skill
  • 60Tools and files. Uses tools (web) that frontmatter does not declare
  • 70Inputs and preconditions. Inputs and preconditions are listed
  • 70Execution cost. Instruction body is 5050 tokens
  • 100Steps. 37 steps
  • 100Failures and branches. 1 branches, has a failure section
  • 100Consistency. Name and required fields are in place
  • 100Running it twice. Mutating operations check current state
  • 100Progress reporting. Reports progress
  • medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
  • low 14 top-level sections: this looks like several domains in one skill

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
  • +1No license
  • +2Single-language instructions
  • +3Description length 291: enough signal without eating the budget
  • +4Structure: 20 headings
  • +3Step-by-step instructions: 37 items
  • +4Has examples (8 code blocks)

Quality base 70; lint remarks subtract, signals add up to 100. Result: 73.