BC triage-validation
Finding validation before writing any report — 7-Question Gate (all 7 questions), 4 pre-submission gates, always-rejected list, conditionally valid with chain table, CVSS 3.1 quick reference, severity decision guide, report title formula, 60-second pre-submit checklist. Use BEFORE writing any report. One wrong answer = kill the finding and move on. Saves N/A ratio.
Finding validation before writing any report — 7-Question Gate (all 7 questions), 4 pre-submission gates, always-rejected list, conditionally valid with chain…
As a process C 51/100 · Has gaps — weak spots: result and completion, inputs and preconditions, running it twice
How to improve
- The SKILL.md body is over 5,000 tokens: move reference detail into references/ and load it when needed.
- 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 · 3
✓ No critical or high findings
Medium and low: 3
-
low Risky intent
intent-offensive-securitySKILL.md:44Offensive-security / dual-use content (legitimate for authorised testing; review intended use)- **High**: Mass PII exfil, privilege escalation, internal SSRF with data, stored XSS all users
-
low Risky intent
intent-offensive-securitySKILL.md:176Offensive-security / dual-use content (legitimate for authorised testing; review intended use) (detector / deny-list definition)[ ] Google: "TARGET_NAME ENDPOINT_NAME bug bounty"
detector -
low Concealment
en-hide-from-userSKILL.md:396Instruction to hide actions from the user (negated — the text forbids it)The retraction template in the RETRACTION DISCIPLINE section above is the canonical format. Don't silently delete — append a retraction appendix to the engagement report instead.
negated
Files scanned: 1. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
body-longSKILL.md body ≈ 5403 tokens (recommended < 5000); move details to references/ - note
frontmatter-keyunknown frontmatter key "sources"
Process rating: all ten parameters 51/100
- 0Result and completion. Does not say what the result is
- 0Inputs and preconditions. Does not say what the process needs to start
- 0Progress reporting. Says nothing while it works
- 30Running it twice. 13 mutating operations with no state check
- 50When it triggers. No condition that starts the skill
- 55Failures and branches. 1 branches
- 60Tools and files. Uses tools (web) that frontmatter does not declare
- 70Execution cost. Instruction body is 5403 tokens
- 100Steps. 50 steps
- 100Consistency. Name and required fields are in place
- medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
- low 12 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 367: enough signal without eating the budget
- +4Structure: 31 headings
- +3Step-by-step instructions: 50 items
- +4Has examples (9 code blocks)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 73.