CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

reverser-android-malware

Android APK malware analysis — manifest permission review, smali disassembly, Java decompilation with jadx, dynamic instrumentation with Frida, network traffic interception, native library analysis, and automated scanning with MobSF.

Quality

80%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

High

Do not use without reviewing

Fix and improve this skill with Tessl

tessl review fix ./packages/decepticon/decepticon/skills/standard/reverser/android-malware/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

78%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 excellent, dense operational reference: nearly every line is an executable command or a high-signal table, with a clear staged workflow, decision gate, and error-recovery table. The two weaknesses are mild duplication in the Quick Reference and a monolithic structure — the inline Frida scripts and indicator tables belong in scripts/ and references/ files to slim the SKILL.md overview.

Suggestions

Move the Frida hook scripts (hook_crypto.js, ssl_bypass.js) into a scripts/ directory and reference them by path, converting ~50 lines of inline JavaScript into a one-line pointer.

Split the MITRE ATT&CK mapping, Detection Signatures, and Tools & Resources tables into a references/ file (e.g. references/indicators.md), keeping the SKILL.md body as a lean workflow overview with well-signaled one-level-deep pointers.

Drop or shrink the Quick Reference section since it duplicates the apktool, jadx, apksigner, and MobSF commands already shown in sections 1, 2, and 7.

DimensionReasoningScore

Conciseness

The body is almost entirely executable commands, terse comments, and dense tables that assume Claude's competence. Minor redundancy exists: the Quick Reference section repeats the apktool, jadx, apksigner, and MobSF commands that appear again in sections 1, 2, and 7. Fits the 4 anchor (efficient with minor trimmable content) rather than 5 (duplication present).

4 / 5

Actionability

Fully executable, copy-paste-ready guidance throughout: concrete bash commands, a complete working Frida JS hook script, MobSF REST API curl calls, specific grep patterns, and readelf/strings recipes. Common cases including obfuscation, SSL pinning, and native packers are covered, matching the 5 anchor.

5 / 5

Workflow Clarity

A clear numbered sequence (static structure → decompile → smali → dynamic → network → native → automated) plus a Decision Gate for branching and an Error Handling table with explicit recovery paths. Matches the 4 anchor: most checkpoints present, but minor gaps — e.g., no explicit verification that decompilation output exists before grep, and section ordering is implied rather than justified. Not 5 because validation checkpoints are implicit; not 3 because error-recovery feedback loops are explicitly tabulated.

4 / 5

Progressive Disclosure

The 320-line body is well-sectioned with clear headers, but there are no bundle files at all: the ~40-line Frida hook script is inlined even though it is invoked as a file ('frida -U -l hook_crypto.js'), and the MITRE mapping, detection signatures, and error-handling tables would naturally live in reference files. Matches the 3 anchor (content that should be separate is inline); not 4 because no one-level-deep references exist and the body is substantial.

3 / 5

Total

16

/

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, tool-anchored description that clearly states what the skill does across the full analysis pipeline. Its main weakness is the missing 'Use when...' trigger clause in the description itself, which both caps completeness and leaves natural-language trigger synonyms only in the metadata.when_to_use field.

Suggestions

Append a 'Use when...' clause to the description, e.g. 'Use when analyzing suspicious Android APKs, mobile malware, banking trojans, or stalkerware', to satisfy the completeness dimension.

Fold the natural trigger terms currently buried in metadata.when_to_use (e.g. 'banking trojan', 'dropper', 'spyware', 'sms stealer') into the description itself so they are visible at trigger time.

DimensionReasoningScore

Specificity

The description lists seven concrete, specific actions ('manifest permission review, smali disassembly, Java decompilation with jadx, dynamic instrumentation with Frida, network traffic interception, native library analysis, and automated scanning with MobSF') with named tools, giving comprehensive coverage of the workflow.

5 / 5

Completeness

The 'what' is clearly and comprehensively stated, but the description contains no 'Use when...' clause or equivalent trigger guidance, capping completeness at 3 per the rubric guideline. Trigger terms exist only in the separate metadata.when_to_use field, not in the description.

3 / 5

Trigger Term Quality

Good natural keyword coverage ('Android APK malware analysis', 'jadx', 'Frida', 'MobSF'), but common user phrases like 'banking trojan', 'reverse engineer', 'decompile', or 'spyware' are missing from the description itself. Fits the 4 anchor (good coverage, a few natural terms missing) rather than 5 (no synonym/variation coverage beyond tool names).

4 / 5

Distinctiveness Conflict Risk

'Android APK malware analysis' with tool-specific terms (jadx, Frida, MobSF, smali) defines a clear niche with minimal overlap risk against general Android development or non-mobile malware skills.

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/reverser/android-malware/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.