iot-security

IoT device security reconnaissance — firmware extraction, embedded analysis, protocol identification, default credential checking, vulnerability scanning, device fingerprinting.

Quality

66%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Critical

Do not install without reviewing

Fix and improve this skill with Tessl

tessl review fix ./packages/decepticon/decepticon/skills/standard/recon/iot-security/SKILL.md

Quality

Content

50%Weight 40%Scale 1-3

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

The skill is a broad, well-organized IoT reconnaissance command catalog with many real, usable commands, but it is weakened by several apparently fictional tools, a lack of validation checkpoints for destructive operations, and a monolithic single-file structure with no progressive disclosure.

Suggestions

Replace or verify the speculative tools (iot-scanner, iot-vuln-scanner, zigbee-scan, zwave-scan, upnp-discover, secrets-collection, routerpasswd) with real, installable equivalents or clearly mark them as illustrative placeholders.

Add explicit validation/verification checkpoints after destructive or batch steps (firmware extraction, flashing, exploitation) so the workflow has feedback loops.

Split the large catalog into one-level-deep reference files (e.g., FIRMWARE.md, PROTOCOLS.md, WIRELESS.md) and keep SKILL.md as a concise overview with signaled links, improving progressive disclosure.

Dimension	Reasoning	Score
Conciseness	The body is mostly lean command blocks with brief comments and avoids explaining concepts Claude already knows, but the ~350-line catalog spanning 10 broad sections could be tightened; it sits at 'mostly efficient but could be tightened' rather than the lean score-3 anchor.	2 / 3
Actionability	Many commands are concrete and copy-paste ready, but several referenced tools appear to be fictional and non-executable ('iot-scanner', 'iot-vuln-scanner', 'zigbee-scan', 'zwave-scan', 'upnp-discover', 'secrets-collection', 'routerpasswd'), so it is not fully executable as the score-3 anchor demands.	2 / 3
Workflow Clarity	Content is organized into numbered sections but is a reference catalog rather than a sequenced process, and risky/destructive operations (firmware flashing, exploitation, persistence) lack validation checkpoints; per the guidelines, missing validation for destructive ops caps workflow clarity at 2.	2 / 3
Progressive Disclosure	No bundle files (references/scripts/assets) exist and the large reference catalog is inline in one file; while sections are well-organized, content that would benefit from being split into separate one-level-deep reference files is kept inline, matching the score-2 anchor.	2 / 3
	Total	8 / 12 Passed

Description

82%Weight 40%Scale 1-3

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, trigger-rich, and distinct, but lacks an explicit 'Use when…' clause, which caps completeness at 2. Adding a when-to-use sentence would raise the completeness and distinctiveness floor.

Suggestions

Append an explicit 'Use when…' clause naming concrete trigger situations (e.g., 'Use when analyzing IoT/embedded device security, extracting firmware, or testing MQTT/CoAP/Modbus devices').

Surface the protocol keywords already in metadata (MQTT, CoAP, Modbus) directly in the description so trigger coverage matches natural user phrasing.

Consider trimming 'embedded analysis', which is slightly more jargon than the other concrete actions, in favor of a more user-natural term.

Dimension	Reasoning	Score
Specificity	The description enumerates multiple concrete actions — 'firmware extraction, embedded analysis, protocol identification, default credential checking, vulnerability scanning, device fingerprinting' — matching the score-3 anchor of listing several specific actions rather than vague language.	3 / 3
Completeness	It clearly answers 'what' the skill does but contains no 'Use when…' clause or equivalent explicit trigger guidance, so per the judging guidelines completeness is capped at 2; it is not a 1 because the 'what' is strong and unambiguous.	2 / 3
Trigger Term Quality	It surfaces natural terms a user would actually say — 'IoT device security', 'firmware extraction', 'default credential checking', 'vulnerability scanning', 'device fingerprinting' — giving good coverage of the domain's common phrasings.	3 / 3
Distinctiveness Conflict Risk	The 'IoT device security reconnaissance' framing carves out a clear niche with distinct triggers, making it unlikely to fire for unrelated skills; it is well above the generic, conflicting examples at score 1.	3 / 3
	Total	11 / 12 Passed

Validation

93%

Warnings & errors only

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

Criteria	Description	Result
metadata_version	'metadata.version' is missing	Warning

	Total	15 / 16 Passed

Repository: PurpleAILAB/Decepticon
Path: packages/decepticon/decepticon/skills/standard/recon/iot-security/SKILL.md
Commit: e34afba

Reviewed: 6 days ago

Table of Contents

Discovery Implementation Validation

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.