SKILLEMALL.ai
GitHub ↗ RU Sign in

BC airtable

Airtable REST API via curl. Records CRUD, filters, upserts.

NousResearch/hermes-agent Hermes author: NousResearch MIT 1 file body ≈ 2 723 tokens Open the sourcegithub.com↗ analyzed 2 d ago

Airtable REST API via curl.

As a process C 64/100 · Has gaps — weak spots: result and completion, progress reporting

IntegrationAirtableSoftware developmentPersonal productivityCommercetype and topics are labelled automatically from the skill text
Runs in: Hermes Agent
JSON
Technical rating
B
82/100
safety, quality, tests
Safety 60%
94
Quality 40%
64
Run on models
none yet
Process rating
C
64/100
Has gaps
Result and completion w 14
0
Progress reporting w 2
0
When it triggers w 12
50
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

  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 · 2

✓ No critical or high findings

Medium and low: 2
  • medium Exfiltration net-credential-use SKILL.md:197
    Credential used in a network call (verify the destination is the intended service)
    RESP=$(curl -s "$URL" -H "Authorization: Bearer $AIRTABLE_API_KEY")
  • low Exfiltration net-credential-use SKILL.md:206
    Credential used in a network call (verify the destination is the intended service) (the skill's own vendor host)
    1. **Confirm auth.** `curl -s -o /dev/null -w "%{http_code}\n" https://api.airtable.com/v0/meta/bases -H "Authorization: Bearer $AIRTABLE_API_KEY"` — expect `200`.
    vendor-host

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

Against the Agent Skills spec

  • warning description-no-when neither description nor a "## When to Use" section says when to use the skill
  • note frontmatter-key unknown frontmatter key "prerequisites"
  • note edit-residue the text marks something as outdated (lines 19): 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
  • 0Progress reporting. Says nothing while it works
  • 50When it triggers. No condition that starts the skill
  • 60Tools and files. Uses tools (bash, web, python) that frontmatter does not declare
  • 60Consistency. The Hermes dialect needs category and tags
  • 70Inputs and preconditions. Inputs and preconditions are listed
  • 100Steps. 36 steps
  • 100Failures and branches. 2 branches, has a failure section
  • 100Execution cost. Instruction body is 2723 tokens
  • 100Running it twice. Mutating operations check current state
  • 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)
  • +3Description length 59: 120–800 characters recommended
  • +3Output format is not stated: the model decides each time
  • -5TODO / placeholder text left in the skill
  • +2Single-language instructions
  • +4Structure: 23 headings
  • +3Step-by-step instructions: 36 items
  • +4Has examples (16 code blocks)
  • +1License stated

Quality base 70; lint remarks subtract, signals add up to 100. Result: 64.