CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

openclaw-traffic-guardian

OpenClaw runtime traffic monitoring baseline for opt-in HTTP/HTTPS proxy inspection, egress detection, inbound injection detection, and social-account policy review.

Quality

63%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./skills/openclaw-traffic-guardian/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

52%Weight 40%Scale 1-5

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The body is well-organized with a sound safety contract and an unusually rigorous signed-release verification flow, but it is a specification pointing at structure that does not exist: SPEC.md is missing, the referenced folders are empty placeholders, and the long verification script is inlined rather than bundled. As shipped, a builder cannot follow the skill's own first instruction.

Suggestions

Ship SPEC.md (or remove the 'Read SPEC.md before implementing' instruction) so the skill's central reference resolves.

Move the ~70-line release verification script into scripts/verify-release.sh and keep a one-line invocation plus the pinned pubkey fingerprint in SKILL.md.

Add a validation checkpoint at the end of 'Required First Implementation Behavior' (e.g. run the test/ suite and confirm redaction on a fixture) so the build workflow has a feedback loop like the install flow already does.

DimensionReasoningScore

Conciseness

The body is mostly efficient — sections are short and the Safety Contract is a lean bullet list — but the ~70-line inline bash verification script (RELEASE_PUBKEY_SHA256, verify_manifest_file, archive hash checks) is content that belongs in a script file, and 'Required First Implementation Behavior' item 6 is a long run-on sentence. This matches 'mostly efficient but includes some unnecessary explanation or could be tightened' rather than anchor 4, where only minor trimming would be needed.

3 / 5

Actionability

There is genuinely executable guidance — the install command and the verification script are copy-paste ready with real error handling — but the core build instruction 'Read `SPEC.md` before implementing' points to a file that does not exist in the bundle, and the Builder Entry Points table maps to placeholder folders (lib/, hooks/, test/) that are absent. This sits at anchor 3: 'some concrete guidance but incomplete; missing key details'.

3 / 5

Workflow Clarity

The install-and-verify workflow has a clear sequence with explicit validation checkpoints and error feedback loops — 'Only install or extract the archive after this verification succeeds', fingerprint mismatch and checksum-mismatch branches that 'exit 1' with actionable messages — plus a numbered 9-step implementation checklist. It falls short of anchor 5 because the implementation steps have no verification step and the build workflow ends at requirements with no feedback loop.

4 / 5

Progressive Disclosure

Scored against the actual bundle (scripts/ holds only a .gitkeep; no references/, assets/, or SPEC.md): the central reference 'Read `SPEC.md` before implementing' dangles, and the 70-line verification script is inlined in SKILL.md instead of living in scripts/. This matches anchor 2 — 'content that clearly belongs in separate files is inlined' — rather than anchor 3, since the primary detailed document the skill depends on is missing entirely, not merely under-signaled.

2 / 5

Total

12

/

20

Passed

Description

58%Weight 40%Scale 1-5

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

The description is specific and sits in a well-delineated niche, but it reads as a compressed spec summary rather than trigger-oriented guidance. It answers 'what' concretely but omits any 'when to use this' phrasing, and it lacks the natural-language synonyms a user would actually type.

Suggestions

Add an explicit trigger clause, e.g. 'Use when building or reviewing OpenClaw runtime traffic monitoring, proxy inspection, or agent egress/exfiltration controls.'

Include natural synonyms users would say — 'exfiltration', 'leak detection', 'network traffic', 'MITM/HTTPS inspection' — alongside the current jargon.

State the observable outcomes (redacted JSONL findings, status command) so the 'what' covers what the skill actually produces.

DimensionReasoningScore

Specificity

The description lists several concrete capabilities — 'opt-in HTTP/HTTPS proxy inspection, egress detection, inbound injection detection, and social-account policy review' — which matches the anchor 'lists several specific actions; minor gaps in coverage'. It falls short of anchor 5 because the actions are stated as a jargon-dense noun phrase for a 'baseline' spec, with coverage gaps (no mention of logging, findings output, or the status/redaction behaviors the body details).

4 / 5

Completeness

The 'what' is clear (runtime traffic monitoring baseline with four named capabilities), but there is no 'Use when...' clause or equivalent explicit trigger guidance, which the judging guidelines state caps completeness at 3. It is not a 2 because the 'what' is concrete and multi-part rather than vague.

3 / 5

Trigger Term Quality

It contains some relevant keywords users might say ('traffic monitoring', 'proxy inspection', 'egress detection'), matching the anchor 'some relevant keywords but missing common variations or synonyms'. Natural user phrasings like 'exfiltration', 'network monitoring', 'MITM', or 'leak detection' are absent, keeping it below anchor 4.

3 / 5

Distinctiveness Conflict Risk

'OpenClaw runtime traffic monitoring' carves out a clear niche with distinct triggers (proxy inspection, egress/inbound-injection detection, social-account policy review), matching 'mostly distinct; minor overlap risk'. It is not a 5 because generic terms like 'traffic monitoring' and 'egress detection' could still overlap with other security or network-monitoring skills.

4 / 5

Total

14

/

20

Passed

Validation

93%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

frontmatter_unknown_keys

Unknown frontmatter key(s) found; consider removing or moving to metadata

Warning

Total

15

/

16

Passed

Repository

prompt-security/clawsec

Path

skills/openclaw-traffic-guardian/SKILL.md

Reviewed

Table of Contents

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.