AC security-audit
Comprehensive security scanning and vulnerability detection. Includes input validation, path traversal prevention, CVE detection, and secure coding pattern enforcement. Use when: authentication implementation, authorization logic, payment processing, user data handling, API endpoint creation, file upload handling, database queries, external API integration. Skip when: read-only operations on public data, internal development tooling, static documentation, styling changes.
Promises comprehensive security scanning: input validation, path traversal prevention, CVE detection, and secure coding patterns. Covers authentication, payments, file uploads, and API endpoints on paper.
Three files with scripts and rules included. Safety score 100, quality 87, but process score lags at 61. Both sandbox scripts exited with code 133—a runtime issue, not logic failure. No critical or high findings, linter clean. Compatible with Claude, Cursor, and other platforms.
Install if you can debug exit code 133 in the scripts or use it as rules only. For production audits, verify why scripts fail first.
Comprehensive security scanning and vulnerability detection.
As a process C 61/100 · Has gaps — weak spots: result and completion, when it triggers, failures and branches
The same skill appears in 1 more place: RA-Skills
How to improve
- 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 · 0
✓ No critical or high findings
Files scanned: 3. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
✓ No remarks against the Agent Skills spec
Process rating: all ten parameters 61/100
- 0Result and completion. Does not say what the result is
- 0Failures and branches. Linear process with no failure handling
- 0Progress reporting. Says nothing while it works
- 20When it triggers. No condition that starts the skill
- 70Inputs and preconditions. Inputs and preconditions are listed
- 100Tools and files. No external tools needed
- 100Steps. 16 steps
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 691 tokens
- 100Running it twice. No mutating operations
- 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)
- +3Output format is not stated: the model decides each time
- +1No license
- +2Single-language instructions
- +3Description length 476: enough signal without eating the budget
- +4Structure: 17 headings
- +3Step-by-step instructions: 16 items
- +4Has examples (13 code blocks)
- +3All 2 scripts are documented
Quality base 70; lint remarks subtract, signals add up to 100. Result: 87.
In the sandbox The scripts kept to themselves
The skill's scripts were run in a throwaway machine: no network, fake keys in the home directory, a tracer watching. We wrote down what they did. Reaching for the network or for secrets caps the technical grade at C; a quiet run adds no points.
Запущено 2 скрипта; каждому дали двадцать секунд, поддельный домашний каталог с ключами и сеть, в которой ничего нет.
scripts/cve-remediate.sh | завершился с кодом 133 |
scripts/security-scan.sh | завершился с кодом 133 |
4 Oct 2026