BD clawguard
🦞 AI-era digital asset proof system | Full format support | Offline-first | Local blockchain | ISO 27001 security
As a process D 49/100 · Unfinished process — weak spots: result and completion, when it triggers, 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.
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 · 4
✓ No critical or high findings
Medium and low: 4
-
low Risky intent
intent-offensive-securityREADME.md:75Offensive-security / dual-use content (legitimate for authorised testing; review intended use)# 勒索病毒防护 / Ransomware Protection
-
low Risky intent
intent-offensive-securityREADME.md:77Offensive-security / dual-use content (legitimate for authorised testing; review intended use) (detector / deny-list definition)clawguard, ransomware C:/Important
detector -
low Risky intent
intent-offensive-securityskill-card.md:14Offensive-security / dual-use content (legitimate for authorised testing; review intended use)External users, developers, and digital-asset creators use this skill to record hashes and timestamps for files, generate proof certificates, verify prior proof IDs, export local records, and run loca
-
low Risky intent
intent-offensive-securityskill-card.md:26Offensive-security / dual-use content (legitimate for authorised testing; review intended use)Risk: The artifact makes legal, ransomware, and security-scan claims that should not be treated as independently validated. <br>
Files scanned: 16. 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")
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
- 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
- 40Consistency. Frontmatter name (clawguard) differs from the folder (clawguard-release)
- 100Tools and files. No external tools needed
- 100Steps. 15 steps
- 100Execution cost. Instruction body is 341 tokens
- 100Running it twice. No mutating operations
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)
- +3Description length 114: 120–800 characters recommended
- +3Output format is not stated: the model decides each time
- +1No license
- +2Single-language instructions
- +4Structure: 11 headings
- +3Step-by-step instructions: 15 items
- +4Has examples (4 code blocks)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 69.
External checks
ClawHub: suspicious
ClawGuard is mostly a local proofing/security utility, but it asks for broad local scan and maintenance authority with weak scoping and some misleading security assurances.
LLM: suspicious (high) · VirusTotal: · 28 May 2026