path-traversal-finder
Path Traversal Finder - Auto-activating skill for Security Fundamentals. Triggers on: path traversal finder, path traversal finder Part of the Security Fundamentals skill category.
36
3%
Does it follow best practices?
Impact
98%
0.98xAverage score across 3 eval scenarios
Passed
No known issues
Optimize this skill with Tessl
npx tessl skill review --optimize ./planned-skills/generated/03-security-fundamentals/path-traversal-finder/SKILL.mdQuality
Discovery
7%Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.
This description is essentially a title repeated with minimal elaboration. It fails to describe what the skill actually does, provides no meaningful trigger terms beyond the skill's own name, and lacks any explicit guidance on when Claude should select it. It would be nearly indistinguishable from a generic security skill in a multi-skill environment.
Suggestions
Add concrete actions the skill performs, e.g., 'Detects path traversal vulnerabilities in code by identifying unsanitized file path inputs, ../ sequences, and directory escape patterns.'
Add an explicit 'Use when...' clause with natural trigger terms like 'directory traversal', '../', 'file path vulnerability', 'LFI', 'local file inclusion', 'path manipulation'.
Remove the redundant repeated trigger term and replace with diverse, natural keywords users would actually use when seeking help with this type of vulnerability.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | The description names the domain ('path traversal') but does not describe any concrete actions. There is no mention of what the skill actually does—no verbs like 'detect', 'scan', 'analyze', or 'report'. It reads more like a label than a capability description. | 1 / 3 |
Completeness | The description fails to answer 'what does this do' beyond naming itself, and the 'when' clause is essentially just restating the skill name as a trigger phrase. There is no explicit 'Use when...' guidance with meaningful context. | 1 / 3 |
Trigger Term Quality | The only trigger term listed is 'path traversal finder' repeated twice. It misses natural variations users would say such as 'directory traversal', '../', 'dot-dot-slash', 'file inclusion vulnerability', 'LFI', or 'path manipulation'. Coverage is extremely narrow. | 1 / 3 |
Distinctiveness Conflict Risk | The term 'path traversal' is fairly specific to a particular vulnerability class, which provides some distinctiveness. However, the vague framing ('Security Fundamentals' category) and lack of concrete actions could cause overlap with other security-related skills. | 2 / 3 |
Total | 5 / 12 Passed |
Implementation
0%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This skill is essentially a placeholder or template with no actual instructional content. It describes what a path traversal finder skill would do in abstract terms but provides zero actionable guidance—no code, no patterns, no detection techniques, no examples of path traversal attacks or defenses. It fails on every dimension of the rubric.
Suggestions
Add concrete, executable code examples showing how to detect path traversal patterns (e.g., regex for '../', URL-encoded variants, canonicalization checks) in at least one language.
Define a clear workflow: 1) Identify user-controlled file path inputs, 2) Check for traversal patterns, 3) Apply canonicalization and validate against allowed directories, 4) Test with known payloads.
Include specific path traversal payloads and patterns to detect (e.g., '../', '..\', '%2e%2e%2f', null bytes) and concrete mitigation code (e.g., os.path.realpath() comparison in Python).
Remove all meta-description sections (Purpose, When to Use, Example Triggers, Capabilities) and replace with actual technical content that teaches Claude how to find and remediate path traversal vulnerabilities.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The content is padded with generic filler text that provides no actionable information. Phrases like 'Provides step-by-step guidance' and 'Follows industry best practices' are empty platitudes. The entire file explains what the skill supposedly does without ever actually doing it. | 1 / 3 |
Actionability | There is zero concrete guidance on path traversal detection or prevention—no code examples, no specific patterns to look for (e.g., '../', '%2e%2e'), no commands, no tools, no regex patterns, no validation logic. The skill describes rather than instructs. | 1 / 3 |
Workflow Clarity | No workflow, steps, or process is defined. The skill claims to provide 'step-by-step guidance' but contains none. For a security-related task involving vulnerability detection, the complete absence of any sequenced process or validation checkpoints is a critical gap. | 1 / 3 |
Progressive Disclosure | The content is a monolithic block of generic marketing-style text with no references to supporting files, no structured sections with real content, and no bundle files to reference. The sections that exist (Purpose, When to Use, Capabilities) are all meta-description with no substance. | 1 / 3 |
Total | 4 / 12 Passed |
Validation
81%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 9 / 11 Passed
Validation for skill structure
| Criteria | Description | Result |
|---|---|---|
allowed_tools_field | 'allowed-tools' contains unusual tool name(s) | Warning |
frontmatter_unknown_keys | Unknown frontmatter key(s) found; consider removing or moving to metadata | Warning |
Total | 9 / 11 Passed | |
- Commit
13d35b8
- 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.