CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

quishing

QR-code phishing (Quishing) — generate QR lures embedding credential-harvest URLs, embed in PDF or email bodies, bypass email gateway URL scanners that cannot parse QR image payloads.

Quality

79%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Critical

Do not install without reviewing

Fix and improve this skill with Tessl

tessl review fix ./packages/decepticon/decepticon/skills/standard/phisher/quishing/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

76%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.

Highly actionable, executable content with a clear decision-gated workflow and good section organization. The main weaknesses are the absence of validation/verification checkpoints before batch campaign delivery (capping workflow clarity) and minor duplication between the prerequisites, tools table, and quick-reference sections.

Suggestions

Add explicit validation steps to the workflow, e.g. decode-test each generated QR variant with a scanner/zbarimg before embedding, and test-send the lure to a controlled inbox to confirm the CID image renders and the QR resolves.

Trim duplication: the Tools & Resources table largely restates the Prerequisites, and the styled-QR Quick Reference block overlaps section 1's generation code — consolidate into one place.

Consider moving the Detection Signatures table and the EvilQR setup into a separate reference file to keep SKILL.md as a leaner overview, since neither is needed for the core generation-and-embed workflow.

DimensionReasoningScore

Conciseness

The body is efficient and code-dominated with little concept padding, but minor trimmable instances exist: the 'Tools & Resources' table partially duplicates the Prerequisites section (qrcode, GoPhish, EvilQR, exiftool all listed twice), and the intro paragraph explains gateway behavior Claude could largely infer. Fits the score-4 anchor ('Efficient; minor instances of over-explanation that could be trimmed') rather than 5.

4 / 5

Actionability

Fully executable, copy-paste-ready code throughout: QR generation (plain and styled), logo overlay, PDF build with fpdf2, GoPhish template HTML and API call for the landing page, and EvilQR setup commands — with consistent placeholder conventions (<LURE_DOMAIN>, {{.RId}}). Matches the score-5 anchor 'Fully executable; copy-paste ready code or commands; specific examples cover the common cases'.

5 / 5

Workflow Clarity

The sequence is clear (numbered sections 1-5 with a Decision Gate and error-handling section), but the workflow is a batch email-campaign operation with no validation or verification steps — e.g., no decode-test of the generated QR, no test send to a controlled inbox before campaign launch, no check that the CID image resolves. Per the judging guidelines, missing validation in batch operations caps workflow clarity at 3.

3 / 5

Progressive Disclosure

Good structure: well-organized single-level sections (Prerequisites, Quick Reference, numbered steps, OPSEC, Decision Gate, Evidence) with no nested or buried references and no bundle files to navigate. Minor gaps: at ~260 lines, content like the Detection Signatures table and EvilQR setup could live in reference files, and the Quick Reference section's larger code blocks slightly duplicate section 1. Fits the score-4 anchor ('Good structure; most content is appropriately placed; minor organization gaps').

4 / 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 specific, distinctive description with concrete multi-action coverage of the capability, but it omits any 'Use when...' trigger clause in the description field itself, capping completeness. Trigger-term coverage is good though missing a few natural synonyms.

Suggestions

Append an explicit trigger clause to the description field, e.g. 'Use when the user asks to create QR-code phishing lures, embed QR codes in phishing PDFs or emails, or bypass email URL scanning.'

Add natural synonyms users might say to the description, such as 'QR code', 'QR phishing', or 'phishing email attachment', rather than relying solely on the metadata when_to_use field.

Consider whether the metadata when_to_use string's redundancy ('qr' appears three times) could be trimmed while adding missing variations like 'QR code lure'.

DimensionReasoningScore

Specificity

The description lists multiple concrete actions — 'generate QR lures embedding credential-harvest URLs, embed in PDF or email bodies, bypass email gateway URL scanners' — comprehensively covering what the skill does. This matches the anchor 'Lists multiple specific concrete actions; comprehensive coverage' and exceeds the score-4 anchor, which expects minor coverage gaps.

5 / 5

Completeness

The 'what' is clear and concrete, but the description field contains no 'Use when...' clause or equivalent explicit trigger guidance, capping completeness at 3 per the judging guidelines. The trigger guidance exists only in the separate metadata 'when_to_use' field, not in the description itself, so the score-4 anchor ('Has both what and when') is not met.

3 / 5

Trigger Term Quality

Good keyword coverage with natural domain terms ('QR-code phishing', 'Quishing', 'QR lures', 'credential-harvest URLs', 'PDF', 'email gateway URL scanners'), but a few natural variations users might say ('QR code', 'QR phishing', 'phishing email attachment') are absent from the description field itself. Fits the score-4 anchor ('Good keyword coverage; a few natural terms missing') rather than 5, which requires comprehensive synonym coverage.

4 / 5

Distinctiveness Conflict Risk

A clear niche (QR-code phishing specifically) with distinct triggers ('Quishing', 'QR lures', 'email gateway URL scanners') and minimal overlap risk with adjacent phishing skills. This matches the score-5 anchor 'Clear niche with distinct triggers; minimal conflict risk'.

5 / 5

Total

17

/

20

Passed

Validation

87%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 14 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

metadata_version

'metadata.version' is missing

Warning

metadata_field

'metadata' should map string keys to string values

Warning

Total

14

/

16

Passed

Repository

PurpleAILAB/Decepticon

Path

packages/decepticon/decepticon/skills/standard/phisher/quishing/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.