CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

iot-overview

Use when the engagement target is IoT, embedded Linux, RTOS, or any device reachable via UART/JTAG/SWD or by extracting its firmware. Covers firmware acquisition, binwalk extraction, filesystem mounting, default-credential hunting, bootloader attacks, wireless protocol sidebands (BLE, Zigbee, Z-Wave, LoRaWAN, sub-GHz).

Quality

88%

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

SKILL.md
Quality
Evals
Security

Quality

Content

80%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.

A well-structured, token-efficient catalog: it routes to ten clearly labeled playbook skills, names concrete bench tools, and sequences a six-step engagement workflow. Its main weakness is the absence of explicit validation checkpoints and error-recovery loops in the workflow, and several steps staying at catalog level rather than giving concrete commands.

Suggestions

Add explicit validation checkpoints to the Workflow, e.g., after acquisition verify the dump against the flash chip's declared size and record a hash, and confirm each filesystem mount succeeded before triage.

Add an error-recovery loop for the extraction step (e.g., if 'binwalk -eM' fails on nonstandard squashfs, fall back to sasquatch/unsquashfs or firmware-mod-kit; if mount fails, try ubifs/ubinize) so failures have a defined retry path.

Make triage steps command-concrete to lift actionability, e.g., 'strings -n 8 fw.bin | grep -iE "pass|key|token"' and the specific mount commands for squashfs/jffs2, rather than delegating all detail to the playbooks.

DimensionReasoningScore

Conciseness

Lean and efficient throughout: a playbook table, a numbered workflow, tool lists, and a short safety note — no explanation of what binwalk/BLE/U-Boot are, no padded prose. Matches the 'every token earns its place' anchor; not score 4 because there is no trimming candidate in the ~50-line body.

5 / 5

Actionability

Includes concrete executable bits — '`binwalk -eM <fw.bin>`, then mount squashfs / jffs2 / ubifs', specific hardware (ch341a + SOIC clip, BusPirate, J-Link), and ordered acquisition tactics (vendor portal first, OTA proxy second, SPI dump third, chip-off last). Not score 5 because most workflow steps remain catalog-level pointers (e.g., 'search strings for credentials' lacks a command) with detail delegated to external playbooks; not score 3 because the concrete commands and named tools make the guidance mostly executable.

4 / 5

Workflow Clarity

The six-step Workflow (inventory → acquire → extract → triage → wireless → cloud) is clearly sequenced with explicit ordering ('vendor update portal first; OTA proxy capture second; SPI flash dump third; eMMC chip-off last'), but validation checkpoints are entirely implicit — no dump-size/hash verification after acquisition, no mount-success check before triage, no error-recovery loop for extraction failures. Matches the 'sequence present but checkpoints missing or implicit' anchor rather than 4, which requires most checkpoints to be present.

3 / 5

Progressive Disclosure

The body is exactly an overview pointing one level deep to well-signaled materials: a Playbooks table mapping each path to its 'Use for' purpose (firmware-acquisition, binwalk-extract, ble-gatt, etc.), with detail appropriately split out. No bundle references/ directory exists, so nothing is inlined that belongs elsewhere; navigation is easy. Matches the top anchor; not score 4 because there are no organization gaps — every section is short and each reference is described.

5 / 5

Total

17

/

20

Passed

Description

92%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.

An excellent description: third-person voice, a concrete 'Use when...' trigger clause, and a comprehensive, specific capability list covering both firmware-level and wireless-sideband work. The only minor gap is a few missing natural synonyms (e.g., 'smart home', 'hardware hacking', '.bin') that would round out trigger-term coverage.

DimensionReasoningScore

Specificity

Lists multiple specific concrete actions — 'firmware acquisition, binwalk extraction, filesystem mounting, default-credential hunting, bootloader attacks, wireless protocol sidebands (BLE, Zigbee, Z-Wave, LoRaWAN, sub-GHz)' — with comprehensive coverage across the domain. Not score 4 because coverage is broad and every action is concrete, with only trivial gaps; not below because nothing is generic.

5 / 5

Completeness

Explicitly answers 'when' with a concrete trigger clause — 'Use when the engagement target is IoT, embedded Linux, RTOS, or any device reachable via UART/JTAG/SWD or by extracting its firmware' — and 'what' with the enumerated capability list ('Covers firmware acquisition, binwalk extraction...'). Matches the top anchor exactly; both what and when are explicit with concrete trigger phrases.

5 / 5

Trigger Term Quality

Strong natural keyword coverage: 'IoT, embedded Linux, RTOS, UART/JTAG/SWD, firmware, binwalk, BLE, Zigbee, Z-Wave, LoRaWAN' — terms a user in this domain would actually say. Not score 5 because a few natural synonyms and variations are missing (e.g., 'smart home', 'hardware hacking/pentest', '.bin' firmware images, 'Flipper Zero'); not score 3 because coverage goes well beyond the domain name.

4 / 5

Distinctiveness Conflict Risk

A clear niche (IoT/embedded device and firmware exploitation plus named wireless protocols) with distinct, domain-specific triggers; minimal overlap risk with adjacent software-pentest or generic security skills. Not score 4 because no closely related skill would plausibly claim these combined hardware+wireless triggers.

5 / 5

Total

19

/

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/iot/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.