CB security-audit
Security audit — save tampering, cheat vectors, network exploits, data exposure, input validation. Before public or multiplayer release.
Security audit — save tampering, cheat vectors, network exploits, data exposure, input validation.
As a process B 66/100 · Nearly there — weak spots: result and completion, inputs and preconditions
How to improve
- Say in the description WHEN to use the skill ("use when…", example requests): that is the agent's main cue.
- 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 · 2
✓ No critical or high findings
Medium and low: 2
-
low Broad scope
meta-dynamic-shellSKILL.md:10Shell command executed automatically when the skill loads (Claude Code !`cmd` preamble)!`bash "${CLAUDE_SKILL_DIR}/../../hooks/yaml-helper.sh" resolve_config --keys automation,workflow` -
low Risky intent
intent-offensive-securitySKILL.md:439Offensive-security / dual-use content (legitimate for authorised testing; review intended use)- **This is not a penetration test** — this audit covers common patterns; a real pentest by a human security professional is recommended before any competitive or monetised multiplayer launch
Files scanned: 1. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
description-no-whendescription does not say WHEN to use the skill (no "use when") - warning
body-longSKILL.md body ≈ 5438 tokens (recommended < 5000); move details to references/ - note
edit-residuethe text marks something as outdated (lines 52): check that old rules are not kept next to new ones — the full check reads the text for contradictions
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
- 50Failures and branches. 0 branches, has a failure section
- 70Execution cost. Instruction body is 5438 tokens
- 85Steps. 43 steps, 1 vague phrases
- 100Tools and files. Tools declared in frontmatter
- 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 The response is described with custom markup (4 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
- +1No license
- +2Single-language instructions
- +3Description length 136: enough signal without eating the budget
- +4Structure: 16 headings
- +3Step-by-step instructions: 43 items
- +4Has examples (2 code blocks)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 62.