SKILLEMALL.ai
RU Sign in

BF Dataguard DLP

Runtime Data Loss Prevention (DLP) for OpenClaw agents. Multi-layer defense against credential exfiltration, PII leakage, and sensitive data transfer. Intercepts outbound tool calls, scans for patterns, and blocks unauthorized data transfers. First ClawHub plugin with real-time data flow protection.

ClawHub Agent Skills author: Jeff C. v2.2.0 MIT-0 17 files · 13 scripts body ≈ 4 660 tokens Open the sourceclawhub.ai↗ analyzed 2 d ago

As a process F 35/100 · Will not run — References files that are not bundled: LICENSE

ProcedureAI and agentsInfrastructuretype and topics are labelled automatically from the skill text
Runs in: OpenClaw Claude / Claude Code ChatGPT / Codex Gemini CLI Cursor GitHub Copilot / VS Code Qwen Code Kimi Code CLI Z.ai (GLM) DeepSeek (Deep Code) Mistral Vibe LangChain (deepagents) Goose OpenCode
JSON
Technical rating
B
80/100
safety, quality, tests
Safety 60%
98
Quality 40%
54
Run on models
none yet
Process rating
F
35/100
Will not run
References files that are not bundled: LICENSE
Tools and files w 18
0
Result and completion w 14
0
Inputs and preconditions w 11
0
the three weakest of ten parameters · all ten

How to improve

  1. Say in the description WHEN to use the skill ("use when…", example requests): that is the agent's main cue.
  2. The text references files that are not there: add them or drop the references.
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 Secrets in code secret-password-literal README.md:76
    Hard-coded password / key literal (may be an example) (placeholder value)
    echo "api_key: sk-test-123" | bash ~/.openclaw/skills/dataguard/scripts/dlp-scan.sh
    placeholder
  • low Risky intent intent-offensive-security SKILL.md:299
    Offensive-security / dual-use content (legitimate for authorised testing; review intended use)
    | T-EXFIL-003 | Credential Harvesting | Prompt injection extracts credentials from files/memory | L1 credential patterns + L2 file read tracking |

Files scanned: 15. Evidence is masked. Grey chips explain why severity was lowered.

Against the Agent Skills spec

  • warning name-format name should be kebab-case (lowercase letters, digits, hyphens)
  • warning description-no-when description does not say WHEN to use the skill (no "use when")
  • warning missing-ref reference to a missing file: LICENSE

Process rating: all ten parameters 35/100

Will not run. References files that are not bundled: LICENSE
  • 0Tools and files. 1 referenced file(s) missing: LICENSE
  • 0Result and completion. Does not say what the result is
  • 0Inputs and preconditions. Does not say what the process needs to start
  • 20When it triggers. No condition that starts the skill
  • 30Running it twice. 12 mutating operations with no state check
  • 40Consistency. Frontmatter name (Dataguard DLP) differs from the folder (dataguard-dlp)
  • 65Failures and branches. 3 branches
  • 70Execution cost. Instruction body is 4660 tokens
  • 100Steps. 64 steps
  • 100Progress reporting. Reports progress
  • medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
  • low 11 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
  • -4Absolute local paths (C:\Users, /home/…): not portable
  • -31 of 8 scripts are never mentioned in SKILL.md
  • +1No license
  • +2Single-language instructions
  • +3Description length 300: enough signal without eating the budget
  • +4Structure: 36 headings
  • +3Step-by-step instructions: 64 items
  • +4Has examples (16 code blocks)

Quality base 70; lint remarks subtract, signals add up to 100. Result: 54.

External checks

ClawHub: suspicious
This appears to be a local DLP tool rather than malware, but its security-control claims and sensitive local logging need careful review before relying on it.
LLM: suspicious (high) · VirusTotal: · 29 May 2026