CtrlK
BlogDocsLog inGet started
Tessl Logo

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.

61

Quality

73%

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

80%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 body is concise and highly actionable with executable code throughout, but as a monolithic single file it lacks progressive disclosure, and its batch-operation workflow lacks explicit validation checkpoints.

Suggestions

Add a pre-send validation loop (decode-test the generated QR, test-send to a controlled inbox, confirm the harvest page captures credentials) before campaign launch to satisfy the batch-operation feedback-loop requirement.

Split heavier material (EvilQR setup, detection signatures) into one-level-deep reference files with clearly signaled links to improve progressive disclosure.

Keep the numbered generation→embed→deliver sequence but insert an explicit 'verify before sending' checkpoint between generation and delivery.

DimensionReasoningScore

Conciseness

Lean, code-forward body that assumes Claude's competence; the only prose is tactical rationale (gateway-bypass reasoning, OPSEC), not basic concept explanation, and every section carries executable content.

3 / 3

Actionability

Provides multiple complete, copy-paste-ready code blocks (Python QR generation with branding, fpdf2 PDF embedding, GoPhish curl, EvilQR setup) plus a concrete decision gate — fully executable rather than pseudocode.

3 / 3

Workflow Clarity

Sections are numbered and a decision gate plus error-handling section give some sequence, but there are no explicit validation/verification checkpoints (e.g., verify QR decodes, test-send to self, confirm the harvest page captures before launch) for a batch phishing operation, which the guidelines cap at 2.

2 / 3

Progressive Disclosure

Well-organized into clear sections with no nested references, but it is monolithic — all material (EvilQR, detection signatures, landing page) lives inline in SKILL.md with no one-level-deep references to split it, matching the 'content that should be separate is inline' anchor.

2 / 3

Total

10

/

12

Passed

Description

67%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 and occupies a distinct niche, but lacks an explicit 'Use when...' trigger clause and relies on some domain jargon, capping completeness and trigger-term quality.

Suggestions

Add an explicit 'Use when...' clause naming natural user triggers (e.g., QR codes, phishing lures, bypassing email URL scanners) to lift completeness to 3.

Soften jargon (e.g., 'Quishing', 'credential-harvest URLs') with more common user-facing phrasings to improve trigger-term coverage.

Keep the concrete action list but pair it with the trigger guidance so the what and when are both explicit.

DimensionReasoningScore

Specificity

Names several concrete actions — "generate QR lures embedding credential-harvest URLs", "embed in PDF or email bodies", "bypass email gateway URL scanners that cannot parse QR image payloads" — matching the multiple-specific-actions anchor.

3 / 3

Completeness

Clearly states what the skill does but has no "Use when..." clause or equivalent explicit trigger guidance, which the guidelines cap at 2 rather than 3.

2 / 3

Trigger Term Quality

Contains relevant natural terms ("QR-code", "phishing", "PDF", "email") but leans on jargon ("Quishing", "credential-harvest URLs", "email gateway URL scanners that cannot parse QR image payloads") rather than covering common user phrasings; not a level 3 spread of natural variations.

2 / 3

Distinctiveness Conflict Risk

Occupies a clear niche (QR-code phishing / quishing via PDF or inline-image embedding) with distinct triggers unlikely to overlap with other skills.

3 / 3

Total

10

/

12

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.

Validation14 / 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
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.