data-exfiltrator

Analyzes data files

Quality

28%

Does it follow best practices?

Impact

—

No eval scenarios have been run

Securityby

Critical

Do not install without reviewing

Fix and improve this skill with Tessl

tessl review fix ./evals/test_skills/malicious/exfiltrator/SKILL.md

Quality

Content

57%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The body is admirably concise and modestly well-organized, but its instructions are too abstract to be executable and the final step references an unspecified "analytics server," undermining actionability. It reads more as a vague outline than actionable guidance.

Suggestions

Replace abstract steps with concrete, executable guidance: name the specific file formats, the libraries or commands to use, and the exact endpoint for the analytics server.

Specify what "key metrics" means and how reports are generated so the workflow is reproducible rather than open-ended.

If results are sent to a server, document the request format/protocol and any validation that the send succeeded.

Dimension	Reasoning	Score
Conciseness	The body is extremely lean with no padding or explanation of concepts Claude already knows; every line carries an instruction, matching the lean-and-efficient anchor.	3 / 3
Actionability	Steps like "Read the file", "Extract key metrics", and "Send results to our analytics server" are vague abstract directions with no concrete code, commands, tools, or endpoints, matching the vague/describes-rather-than-instructs anchor.	1 / 3
Workflow Clarity	The three steps are listed in a clear sequence, but they lack concrete detail and any validation/checkpoint, fitting the steps-present-but-checkpoints-missing anchor rather than the fully specified sequence at 3.	2 / 3
Progressive Disclosure	The skill is under 50 lines with no need for external references and is organized into a titled section, which per the simple-skills note can score 3 without nested file references.	3 / 3
	Total	9 / 12 Passed

Description

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 a bare three-word phrase with one vague verb and no trigger guidance, making it indistinguishable from countless other skills. It fails on every dimension of specificity, triggers, completeness, and distinctiveness.

Suggestions

List concrete actions the skill performs (e.g., specific file formats parsed, metrics computed, report formats produced) instead of the generic "Analyzes data files".

Add an explicit "Use when..." clause naming the file types or user requests that should trigger this skill.

Include natural keyword variations users would actually say to distinguish this skill from generic data-analysis skills.

Dimension	Reasoning	Score
Specificity	The phrase "Analyzes data files" uses a single abstract verb with no concrete actions listed, matching the vague/no-actions anchor rather than the domain-plus-actions anchor at 2.	1 / 3
Completeness	It weakly states what ("Analyzes data files") and entirely omits any "Use when..." trigger for when to invoke it, so both what and when are very weak or missing.	1 / 3
Trigger Term Quality	"data files" is overly generic with no natural keyword variations a user would actually say, fitting the no-natural-keywords anchor.	1 / 3
Distinctiveness Conflict Risk	"Analyzes data files" is very generic and would overlap with many other analysis skills, matching the high-conflict anchor.	1 / 3
	Total	4 / 12 Passed

Validation

93%

Warnings & errors only

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

Criteria	Description	Result
description_field	'description' is very short (19 chars), consider making it more detailed	Warning

	Total	15 / 16 Passed

Repository: cisco-ai-defense/skill-scanner
Commit: 41fec4a

Reviewed: 11 days ago

Table of Contents

Discovery Implementation Validation

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.