CtrlK
BlogDocsLog inGet started
Tessl Logo

aatmf-t02-linguistic-evasion

AATMF T2 — Semantic & Linguistic Evasion. Foreign-language pivot, encoded payloads, esolang, fictional framing, jailbreak via translation.

58

Quality

67%

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/plugins/llm-redteam/t02-linguistic-evasion/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

68%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.

The body is a lean, actionable catalog with concrete probe patterns and an executable YAML config, but it lacks an explicit end-to-end testing workflow with validation checkpoints. Adding a sequenced probe-run-then-verify process would lift workflow clarity.

Suggestions

Add a numbered probe workflow (configure promptfoo YAML -> run -> inspect failures -> iterate top candidates) with explicit validation gates.

Move the per-technique variant lists (e.g., DAN/STAN/AIM personas, encoding schemes) into a references file and link to it, keeping SKILL.md as an overview.

Include a brief "verify bypass" step defining what counts as a confirmed bypass before reporting severity.

DimensionReasoningScore

Conciseness

Technique entries are terse and assume Claude's knowledge (e.g., one-line Brainfuck/Whitespace examples); only minor phrasing could be trimmed further.

4 / 5

Actionability

Provides concrete encoded-payload examples (Base64, ROT13, leet, morse) and a copy-paste promptfoo YAML probe block, with only minor gaps in coverage.

4 / 5

Workflow Clarity

The content is a technique catalog rather than a sequenced workflow; the only checkpoint is "reproducible across 3+ fresh conversations," and batch probe runs lack explicit validate-then-fix loops.

3 / 5

Progressive Disclosure

No bundle files exist; the single SKILL.md is well-organized into Techniques, Probe pattern, Detection, Severity, Defender, and Cross-references sections with a single one-level external reference.

4 / 5

Total

15

/

20

Passed

Description

66%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.

The description names a clear niche and enumerates concrete techniques with some natural trigger terms, but it omits any explicit "Use when..." guidance, capping its completeness. Adding a trigger clause would raise the score meaningfully.

Suggestions

Append a "Use when..." clause naming concrete triggers (e.g., "Use when testing multilingual jailbreaks, encoded-payload bypasses, or fictional-framing attacks").

Add common synonyms/users' phrasing such as "translation bypass", "base64/ROT13 payload", or "roleplay jailbreak" to broaden trigger-term coverage.

Clarify the scope boundary versus a general jailbreak skill to reduce overlap ambiguity.

DimensionReasoningScore

Specificity

Lists several concrete techniques ("Foreign-language pivot, encoded payloads, esolang, fictional framing, jailbreak via translation") rather than vague language, with only minor coverage gaps.

4 / 5

Completeness

The "what" is clear but there is no "Use when..." clause or equivalent explicit trigger guidance, which caps completeness at 3 per the rubric guideline.

3 / 5

Trigger Term Quality

"jailbreak", "translation", and "fictional framing" are natural user terms, though "esolang" and "encoded payloads" lean technical; a few common synonyms are missing.

4 / 5

Distinctiveness Conflict Risk

The AATMF T2 / Semantic & Linguistic Evasion niche is clearly distinct, with only minor overlap risk against a broader jailbreak skill.

4 / 5

Total

15

/

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.

Validation15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

metadata_version

'metadata.version' is missing

Warning

Total

15

/

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.