SKILLEMALL.ai
GitHub ↗ RU Sign in

CB audit-permissions

Audits existing table permissions on a Power Pages site by analyzing them against site code and Dataverse metadata, then GRADES the configuration with deterministic 1–5 scores across 3 security/usability/correctness categories (9 dimensions). Detection is anchored by a recurring-issue catalog so findings and severities stay consistent run-to-run. Generates an HTML report with an at-a-glance verdict and per-category scores in the Overview plus a single list of **major/minor** issues (each major issue labelled permissions-only or upstream-caused with a short justification), and suggested fixes. Use when the user wants to review, verify, check, score, or grade table permissions for security issues. Supports SPA and PAC-downloaded non-SPA sites.

microsoft/power-platform-skills Claude Code author: microsoft MIT 7 files · 4 scripts body ≈ 19 446 tokens Open the sourcegithub.com↗ analyzed 9 d ago

Audits existing table permissions on a Power Pages site by analyzing them against site code and Dataverse metadata, then GRADES the configuration with…

As a process B 67/100 · Nearly there — weak spots: result and completion, inputs and preconditions, execution cost

AnalyzerData and analyticsSoftware developmenttype 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
87/100
safety, quality, tests
Safety 60%
95
Quality 40%
75
Run on models
none yet
Process rating
B
67/100
Nearly there
Result and completion w 14
0
Inputs and preconditions w 11
0
Execution cost w 6
10
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.

Broad scope 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 asks for more than the task needs: broad tool access, credential environment variables, binaries. Every extra permission widens the damage from a mistake or a compromise.

For the author

Narrow allowed-tools and the variable list to the minimum; replace binaries with readable sources or scripts.

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 Broad scope meta-broad-allowed-tools SKILL.md:1
    Broad tool permissions pre-approved: Bash
    allowed-tools: Read Write Bash Glob Grep AskUserQuestion TaskCreate TaskUpdate TaskList Agent

Files scanned: 7. Evidence is masked. Grey chips explain why severity was lowered.

Against the Agent Skills spec

  • warning body-long SKILL.md body ≈ 19446 tokens (recommended < 5000); move details to references/

Process rating: all ten parameters 67/100

  • 0Result and completion. Does not say what the result is
  • 0Inputs and preconditions. Does not say what the process needs to start
  • 10Execution cost. Instruction body is 19446 tokens: crowds the task out of the window
  • 85Steps. 281 steps, 2 vague phrases
  • 100Tools and files. Tools declared in frontmatter
  • 100When it triggers. States when to use and when not to
  • 100Failures and branches. 11 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 16 top-level sections: this looks like several domains in one skill
  • low The response is described with custom markup (21 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
  • -31 of 4 scripts are never mentioned in SKILL.md
  • +1No license
  • +2Single-language instructions
  • +3Description length 751: enough signal without eating the budget
  • +4Structure: 49 headings
  • +3Step-by-step instructions: 281 items
  • +4Has examples (17 code blocks)
  • +4Reference files are cited in the instructions (1 of 1)

Quality base 70; lint remarks subtract, signals add up to 100. Result: 75.