pt-embedded-device-assessment
Performs authorized security assessment of embedded and IoT devices across hardware, firmware, interfaces, and update mechanisms. Use when testing device boot flows, debug interfaces, firmware integrity, and local/network attack surfaces.
91
86%
Does it follow best practices?
Impact
99%
1.12xAverage score across 3 eval scenarios
Passed
No known issues
Quality
Discovery
100%Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.
This is a well-crafted skill description that clearly defines its scope (embedded/IoT security assessment), lists specific capabilities across multiple domains (hardware, firmware, interfaces, update mechanisms), and provides explicit trigger conditions. The description uses appropriate third-person voice and includes domain-specific terminology that users in this field would naturally use.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: 'security assessment of embedded and IoT devices across hardware, firmware, interfaces, and update mechanisms' and 'testing device boot flows, debug interfaces, firmware integrity, and local/network attack surfaces' - these are specific, actionable capabilities. | 3 / 3 |
Completeness | Clearly answers both what ('Performs authorized security assessment of embedded and IoT devices across hardware, firmware, interfaces, and update mechanisms') AND when ('Use when testing device boot flows, debug interfaces, firmware integrity, and local/network attack surfaces') with explicit trigger guidance. | 3 / 3 |
Trigger Term Quality | Includes natural keywords users would say: 'embedded', 'IoT devices', 'hardware', 'firmware', 'boot flows', 'debug interfaces', 'firmware integrity', 'attack surfaces', 'security assessment'. These cover common terminology in the embedded security domain. | 3 / 3 |
Distinctiveness Conflict Risk | Clear niche focusing specifically on embedded/IoT device security with distinct triggers like 'boot flows', 'debug interfaces', 'firmware integrity' that are unlikely to conflict with general security or web application testing skills. | 3 / 3 |
Total | 12 / 12 Passed |
Implementation
72%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This skill provides a well-structured, concise framework for embedded device security assessment with appropriate safety warnings and a useful output template. However, it lacks the concrete, executable guidance that would make it immediately actionable—no specific tools, commands, or techniques are provided for tasks like firmware extraction or interface enumeration. Adding validation checkpoints between workflow steps would improve safety for hardware testing.
Suggestions
Add concrete tool examples for key tasks (e.g., 'Use `binwalk -e firmware.bin` for extraction' or 'Connect UART with `screen /dev/ttyUSB0 115200`')
Include explicit validation checkpoints in the workflow, such as 'Verify device responds before proceeding' or 'Confirm backup exists before firmware modification'
Provide at least one complete example showing interface enumeration output or a sample finding with specific evidence format
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The content is lean and efficient, avoiding explanations of what embedded devices or security testing are. Every section serves a purpose with no padding or unnecessary context. | 3 / 3 |
Actionability | Provides structured guidance and a useful output template, but lacks concrete commands, tool examples, or executable code snippets. Steps like 'firmware extraction' and 'enumerate interfaces' remain abstract without specific techniques or tools. | 2 / 3 |
Workflow Clarity | The 5-step workflow provides clear sequencing, but lacks explicit validation checkpoints or feedback loops. For potentially destructive hardware testing, there should be explicit verify-before-proceeding gates between steps. | 2 / 3 |
Progressive Disclosure | For a skill of this size (~60 lines), the structure is appropriate with clear sections. The content is well-organized with distinct phases (context, workflow, output, checks) without needing external file references. | 3 / 3 |
Total | 10 / 12 Passed |
Validation
100%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 11 / 11 Passed
Validation for skill structure
No warnings or errors.
- Repository
- santosomar/ethical-hacking-agent-skills
- Commit
a8ff73a
- 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.