CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

opcua

OPC-UA (TCP 4840) attack playbook — endpoint enumeration, SecurityPolicy mapping, anonymous/weak-auth abuse, address-space browsing and tag read, HistoryRead exfiltration, Method call for control actions, session-exhaustion DoS. Modern IT/OT DMZ convergence protocol replacing legacy fieldbus.

Quality

83%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Low

Low-risk findings worth noting

SKILL.md
Quality
Evals
Security

Quality

Content

85%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.

An exceptional, fully executable attack playbook with strong sequencing, safety gates for write-class and DoS operations, and concrete evidence requirements. Its only structural weakness is the absence of progressive disclosure — everything is inlined in one long file rather than split across bundle files.

DimensionReasoningScore

Conciseness

The body is dense and code-dominated with almost no explanation of concepts Claude already knows; only minor instances could be trimmed (the vendor-name framing in the intro and some version-specific CVE commentary). It does not reach 5 because a few contextual sentences and inline comments do not strictly earn their place.

4 / 5

Actionability

Every main phase (GetEndpoints, anonymous connect, credential brute force, browse/read, HistoryRead, Method call, session exhaustion) ships complete, copy-paste-ready asyncua scripts with real exception handling, plus nmap commands and evidence snippets covering the common cases. Two supplementary fragments (fingerprint, find_methods) reuse context rather than standing alone but do not gap the main workflow.

5 / 5

Workflow Clarity

Phases 1-7 are explicitly sequenced from discovery to gated exploitation, with validation checkpoints throughout: "Key findings to record" after enumeration, "STOP. Write-class authorization required" before Method calls, a version check advisory before DoS testing, per-node error handling inside loops, and the ZFP two-method evidence checklist. Destructive and batch operations all carry explicit gates, so no cap applies.

5 / 5

Progressive Disclosure

The file is well-organized with clear phase headers, but it is a ~365-line monolith with no bundle files: specialized phases (HistoryRead, Method calls, DoS) and the evidence templates could live in separate scripts/references files loaded only when needed. This fits "content that should be separate is inline" rather than the good-placement anchor at 4.

3 / 5

Total

17

/

20

Passed

Description

75%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.

A highly specific, action-dense description for a narrow ICS/OT protocol niche with excellent distinctiveness. Its main weakness is the absence of an explicit "Use when..." trigger clause, which caps completeness, and natural-synonym trigger terms living in metadata rather than the description itself.

Suggestions

Add an explicit trigger clause, e.g. "Use when enumerating or attacking OPC-UA endpoints (port 4840) on ICS/SCADA/OT engagements, or when the user mentions opcua, unified architecture, or asyncua."

Fold natural keyword variations from metadata.when_to_use (opcua, opc-ua, unified architecture, scada, asyncua) into the description so trigger matching does not depend on the metadata field.

Clarify the authorization posture in the description (e.g. "for authorized security assessments") so the "when" guidance also conveys intended scope.

DimensionReasoningScore

Specificity

The description enumerates multiple concrete attack actions — "endpoint enumeration, SecurityPolicy mapping, anonymous/weak-auth abuse, address-space browsing and tag read, HistoryRead exfiltration, Method call for control actions, session-exhaustion DoS" — with comprehensive coverage of the skill's capabilities, matching the top anchor rather than the 'minor gaps' anchor below it.

5 / 5

Completeness

The "what" is clearly and comprehensively stated, but there is no "Use when..." clause or equivalent explicit trigger guidance; the closing sentence "Modern IT/OT DMZ convergence protocol replacing legacy fieldbus" provides context rather than a trigger, which per the guidelines caps completeness at 3. It is not a 4 because the "when" is only weakly implied.

3 / 5

Trigger Term Quality

Terms like "OPC-UA", "TCP 4840", "SecurityPolicy", "HistoryRead", and "IT/OT" give good natural coverage a practitioner would say, but common variations such as "opcua", "unified architecture", or "SCADA" appear only in metadata.when_to_use and not in the description itself, so it falls just short of the comprehensive-synonyms anchor.

4 / 5

Distinctiveness Conflict Risk

The description is tied to a specific protocol and port ("OPC-UA (TCP 4840) attack playbook") with distinctive domain actions, giving it a clear niche with minimal risk of triggering for the wrong skill.

5 / 5

Total

17

/

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

metadata_version

'metadata.version' is missing

Warning

Total

15

/

16

Passed

Repository

PurpleAILAB/Decepticon

Path

packages/decepticon/decepticon/skills/standard/exploit/ics-ot/opcua/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.