BD HIIC-skill-vetter
Practical skill vetting workflow for AI agents. Prioritizes clear yes/no risk judgments, concise conclusions, and business-aware risk tolerance before installing a skill.
As a process D 49/100 · Unfinished process — weak spots: result and completion, when it triggers, inputs and preconditions
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 · 6
✓ No critical or high findings
Medium and low: 6
-
low Risky intent
intent-offensive-securityREADME.md:13Offensive-security / dual-use content (legitimate for authorised testing; review intended use)- privilege escalation
-
low Risky intent
intent-offensive-securitySKILL.md:29Offensive-security / dual-use content (legitimate for authorised testing; review intended use)- privilege escalation
-
low Risky intent
intent-offensive-securitySKILL.md:65Offensive-security / dual-use content (legitimate for authorised testing; review intended use)• Privilege Escalation: [Yes / No]
-
low Risky intent
intent-offensive-securitySKILL.md:83Offensive-security / dual-use content (legitimate for authorised testing; review intended use)- no privilege escalation found
-
low Dangerous commands
cmd-privilegevet-scan.sh:54Privilege escalation / world-writable permissions (string literal in code, not executed; documentation of a security skill)run_search "ELEVATED PRIVILEGES" 'sudo|setcap|chmod 777|chown root'
code literalsecurity skill
A further 1 matches are quotations in this security skill's documentation and are not counted as findings.
Files scanned: 6. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
name-formatname should be kebab-case (lowercase letters, digits, hyphens)
Process rating: all ten parameters 49/100
- 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
- 20When it triggers. No condition that starts the skill
- 30Running it twice. 2 mutating operations with no state check
- 55Failures and branches. 1 branches
- 60Tools and files. Uses tools (bash) that frontmatter does not declare
- 100Steps. 53 steps
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 1175 tokens
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 170: enough signal without eating the budget
- +4Structure: 14 headings
- +3Step-by-step instructions: 53 items
- +4Has examples (2 code blocks)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 79.