CtrlK
BlogDocsLog inGet started
Tessl Logo

attack-path-analysis

Use when Codex is already in the attack-path-analysis phase of a security scan or the user explicitly asks to trace a security finding from source to sink and calibrate severity. Do not use as the primary trigger for full PR, commit, branch, patch, or repository scans.

70

Quality

86%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Passed

No findings from the security scan

SKILL.md
Quality
Evals
Security

Quality

Content

72%

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

The body is well-structured and highly actionable with appropriate progressive disclosure into real reference files. Its main weakness is mild redundancy across the workflow and checklists, and verification checkpoints that read as considerations rather than explicit gates.

Suggestions

Consolidate the counterevidence guidance that currently repeats across Workflow step 4, the Scope and Attack Path Checklist, and the Counterevidence Checklist into a single authoritative section.

Reframe the 'Before finalizing...' and counterevidence items as explicit validation gates (e.g., 'Stop and verify counterevidence is recorded before finalizing scope') to make checkpoints unambiguous for the batch/multi-candidate flow.

Tighten the overlap between the Workflow service-mapping step (3) and the Scope and Attack Path Checklist, which describe the same service/exposure/identity fields twice.

DimensionReasoningScore

Conciseness

The body is mostly lean with no concept tutorials, but counterevidence and scope/service-mapping guidance recurs across the Workflow, Scope Checklist, and Counterevidence Checklist, so it could be tightened by deduplication.

2 / 3

Actionability

As an instruction-only skill it gives concrete, specific guidance: named fact fields, exact required receipt contents (candidate id, decision, facts/proof gap, artifact reference), a precise output contract, and clearly signaled reference files.

3 / 3

Workflow Clarity

A clear 9-step sequenced workflow with checklists exists, but verification checkpoints are stated as considerations rather than hard validate-gates and overlapping checklists slightly muddy the sequence for a batch/multi-candidate operation.

2 / 3

Progressive Disclosure

Content is organized into well-labeled sections with two real one-level-deep local references (severity-policy.md, attack-path-facts.md) clearly signaled, and the heavy severity policy appropriately lives in a separate file rather than inline.

3 / 3

Total

10

/

12

Passed

Description

100%

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, well-triggered, and self-disambiguating, explicitly defining both when to use and when not to use the skill. It avoids vague fluff and ties cleanly to a distinct phase of a security scan.

DimensionReasoningScore

Specificity

Names concrete actions ('trace a security finding from source to sink and calibrate severity') plus explicit negative scope, matching the 'lists multiple specific concrete actions' anchor.

3 / 3

Completeness

Explicit 'Use when...' clause states the trigger, and 'Do not use...' adds anti-trigger guidance, clearly answering both what and when.

3 / 3

Trigger Term Quality

Uses natural terms a security reviewer would say ('security finding', 'source to sink', 'calibrate severity', 'attack-path-analysis phase') with good coverage rather than generic jargon.

3 / 3

Distinctiveness Conflict Risk

Scoped to a specific scan phase with an explicit anti-trigger against full PR/repo scans, giving it a clear niche unlikely to conflict with sibling skills.

3 / 3

Total

12

/

12

Passed

Validation

100%

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

Validation16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
openai/plugins
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.