AB onionclaw
Search the Tor dark web, fetch .onion hidden-service pages, rotate Tor identities, and run structured multi-step OSINT investigations. Use when the user asks to search the dark web, investigate .onion sites, check whether data appeared on the dark web, fetch a .onion URL, look up leaked credentials, investigate ransomware groups, or conduct any Tor-based threat intelligence or OSINT task.
As a process B 65/100 · Nearly there — weak spots: inputs and preconditions, running it twice
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 · 5
✓ No critical or high findings
Medium and low: 5
-
low Risky intent
intent-offensive-securitySKILL.md:8Offensive-security / dual-use content (legitimate for authorised testing; review intended use)leaked credentials, investigate ransomware groups, or conduct any Tor-based
-
low Risky intent
intent-offensive-securitySKILL.md:182Offensive-security / dual-use content (legitimate for authorised testing; review intended use) (documentation table row)| `ransomware` | Malware / C2 / MITRE ATT&CK TTPs, victim orgs, indicators |
table -
low Risky intent
intent-offensive-securitySKILL.md:209Offensive-security / dual-use content (legitimate for authorised testing; review intended use) (documentation table row)| `--mode MODE` | `threat_intel` | `threat_intel` / `ransomware` / `personal_identity` / `corporate` |
table -
low Risky intent
intent-offensive-securitySKILL.md:267Offensive-security / dual-use content (legitimate for authorised testing; review intended use) (quoted — discussed, not commanded)python3 {baseDir}/pipeline.py --query "ransomware hospital 2026" --watch --interval 6quoted -
low Risky intent
intent-offensive-securitySKILL.md:299Offensive-security / dual-use content (legitimate for authorised testing; review intended use) (quoted — discussed, not commanded)### "Investigate ransomware group X"
quoted
Files scanned: 2. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- note
frontmatter-keyunknown frontmatter key "homepage"
Process rating: all ten parameters 65/100
- 0Inputs and preconditions. Does not say what the process needs to start
- 30Running it twice. 2 mutating operations with no state check
- 55Failures and branches. 1 branches
- 60Tools and files. Uses tools (bash, web, python, node) that frontmatter does not declare
- 60Result and completion. Output format stated, no completion criterion
- 70When it triggers. States when to use, but not when not to
- 100Steps. 18 steps
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 2845 tokens
- 100Progress reporting. Reports progress
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)
- +1No license
- +2Single-language instructions
- +3Description length 391: enough signal without eating the budget
- +4Structure: 24 headings
- +3Step-by-step instructions: 18 items
- +3Output format is stated explicitly
- +4Has examples (18 code blocks)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 86.