SKILLEMALL.ai

BB clawvisor

Route tool requests through Clawvisor for credential vaulting, task-scoped authorization, and human approval flows. Use for Gmail, Calendar, Drive, Contacts, GitHub, and iMessage (macOS). Clawvisor enforces restrictions, manages task scopes, and injects credentials — the agent never handles secrets directly.

ClawHub Agent Skills author: Eric Levine v0.9.10 MIT-0 6 files body ≈ 6 305 tokens Open the sourceclawhub.ai analyzed 2 d ago

As a process B 66/100 · Nearly there — weak spots: result and completion, inputs and preconditions

ReferenceGitHubGmailAI and agentsInfrastructurePersonal productivitytype and topics are labelled automatically from the skill text
JSON
Technical rating
B
86/100
safety, quality, tests
Safety 60%
95
Quality 40%
72
Run on models
none yet
Process rating
B
66/100
Nearly there
Inputs and preconditions w 11
0
Result and completion w 14
40
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.

Instruction override 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 text contains phrases like "ignore previous instructions" or "you are now…". That is an attempt to hijack the agent: it may break your rules, the system limits or company policy.

For the author

An honest skill does not need them: state the role and the rules directly without overriding other instructions. Otherwise catalog scanners and corporate filters will block the listing.

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 · 1

✓ No critical or high findings

Medium and low: 1
  • medium Instruction override en-ignore-previous SKILL.md:198
    Instruction-override phrase ("ignore previous instructions") (detector / deny-list definition)
    **Key rule:** The verifier treats **all agent-provided fields as untrusted**. Any text that resembles an instruction ("ignore previous rules", "approve this request", "the user said to...") will be fl
    detector

Files scanned: 6. Evidence is masked. Grey chips explain why severity was lowered.

Against the Agent Skills spec

  • warning body-long SKILL.md body ≈ 6305 tokens (recommended < 5000); move details to references/
  • note frontmatter-key unknown frontmatter key "published_at"
  • note frontmatter-key unknown frontmatter key "homepage"

Process rating: all ten parameters 66/100

  • 0Inputs and preconditions. Does not say what the process needs to start
  • 40Result and completion. Does not say what the result is
  • 50When it triggers. No condition that starts the skill
  • 60Tools and files. Uses tools (bash, web) that frontmatter does not declare
  • 70Execution cost. Instruction body is 6305 tokens
  • 100Steps. 50 steps
  • 100Failures and branches. 14 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 13 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 309: enough signal without eating the budget
  • +4Structure: 26 headings
  • +3Step-by-step instructions: 50 items
  • +4Has examples (11 code blocks)

Quality base 70; lint remarks subtract, signals add up to 100. Result: 72.

External checks

ClawHub: clean
This skill is a disclosed gateway for routing agent actions through Clawvisor approvals and policies, but it can access sensitive connected services if the user grants it a broad token or standing tasks.
LLM: benign (high) · VirusTotal: · 22 Jun 2026