ffuf-web-fuzzing

SAFE max severity MEDIUMSkillSpector Caution 44 registry jthack last scanned 2026-02-06 1 scan

Verdict safe, but 5 findings (2 medium, 3 low), mainly social engineering, policy violation, skill discovery abuse. Most recent scan 2026-02-06.

This skill provides legitimate penetration testing guidance for the ffuf web fuzzing tool. The security analysis reveals NO CRITICAL or HIGH severity threats. The skill does not contain prompt injection attempts, data exfiltration code, credential theft, command injection vulnerabilities, or other serious security issues. The findings are limited to: (1) missing optional metadata fields that would improve transparency, (2) references to non-existent files that appear to be documentation errors, and (3) a potentially truncated code snippet. The core functionality - providing ffuf usage examples and a helper script for analyzing results - is appropriate for a penetration testing skill. The Python helper script performs legitimate analysis of ffuf JSON output without making network calls, accessing credentials, or executing arbitrary commands. This skill is SAFE for use in penetration testing contexts with the minor improvements noted.
Scanner's overall assessment (LLM analyzer)

Findings5

Critical0

High0

Medium2

Low3

Analyzersstatic behavioral llm trigger meta

Second scanner: NVIDIA SkillSpector

VerdictCaution 44

Score44 / 100

Issues8

CategoriesData Exfiltration Privilege Escalation MCP Least Privilege

Version2.12.0 (static)

Independent static run, no language model, over the same files as the Cisco scan above. How the two scanners compare across the whole corpus: Two scanners, one corpus.

What this skill does

Expert guidance for ffuf web fuzzing during penetration testing, including authenticated fuzzing with raw requests, auto-calibration, and result analysis

Package: 4 files, 33 KB
SKILL.md: 2322 words, 12+ sections
Code: Python (1)

SKILL.md covers: FFUF (Fuzz Faster U Fool) Skill · Overview · Installation · Using Go · Using Homebrew (macOS) · Binary download · Download from: https://github.com/ffuf/ffuf/releases/latest · Core Concepts · The FUZZ Keyword · Multi-wordlist Modes · Common Use Cases · 1. Directory and File Discovery

Findings

MEDIUM SKILL DISCOVERY ABUSE detected by YARA Skill Discovery Abusestatic

Detects manipulation of skill discovery to increase unwanted activation: ALWAYS USE THIS

SKILL.md:112

# Auto-calibration - ALWAYS USE THIS

Remediation: Review and remove skill discovery abuse pattern

MEDIUM Missing Critical Metadata Fields Social Engineeringllm

The skill manifest is missing several important metadata fields including 'license', 'compatibility', and 'allowed-tools'. While 'allowed-tools' is optional per the spec, its absence makes it impossible to verify if the skill's behavior (executing bash commands, reading/writing files) aligns with declared restrictions. The missing license field creates legal ambiguity for users.

SKILL.md

YAML Manifest shows: license: Not specified, compatibility: Not specified, allowed-tools: Not specified

Remediation: Add complete metadata to YAML frontmatter: specify license (e.g., MIT), add compatibility field indicating which environments support this skill, and consider adding allowed-tools declaration (e.g., [Read, Write, Bash, Python]) to make tool usage expectations explicit.

LOW Skill does not specify a license Policy Violationstatic

Skill manifest does not include a 'license' field. Specifying a license helps users understand usage terms.

SKILL.md

Remediation: Add 'license' field to SKILL.md frontmatter (e.g., MIT, Apache-2.0)

LOW References to Non-Existent External Files Data Exfiltrationllm

The skill instructions reference five Python files (dynamic.py, cluttering.py, SecLists.py, Burp.py, your.py) that are not included in the skill package. These appear to be placeholder references or documentation errors rather than actual security threats, but could cause confusion or errors during skill execution.

Referenced files not found: dynamic.py, cluttering.py, SecLists.py, Burp.py, your.py

Remediation: Remove references to non-existent files from the documentation, or include the actual files if they are intended to be part of the skill package. Ensure all referenced files exist within the skill directory structure.

LOW Incomplete Code Snippet in Helper Script Social Engineeringllm

The ffuf_helper.py script contains a truncated code section (ends with 'print(f" {r[\'stat') indicating the file may be incomplete or corrupted. While this appears to be a truncation in the analysis input rather than malicious obfuscation, it could lead to runtime errors if the actual file is similarly incomplete.

ffuf_helper.py:45

Script ends abruptly with: print(f"      {r['stat... (truncated, total 7336 chars)

Remediation: Verify the complete ffuf_helper.py file is included in the skill package. Ensure all Python scripts are syntactically complete and can be parsed without errors. Add error handling for JSON parsing and file operations.

What is in the package

File	Kind	Size
`SKILL.md`	doc	17 KB
`ffuf_helper.py`	script	7.2 KB
`resources/REQUEST_TEMPLATES.md`	doc	4.7 KB
`resources/WORDLISTS.md`	doc	4.4 KB

External hosts referenced

target.com github.com api.target.com fuzz.target.com codingo.io ffuf.me

Hostnames that appear in the skill's files. Referencing a host is not a finding; compare against the findings above and the skill's stated purpose.

Environment variables referenced

DOC_ID USER_ID

Package contents recorded 2026-10-22 at commit 50fd4af4d8bd. The scan above ran against the version current at scan time; the two can differ if the skill has since been updated.

What we checked

Static analyzer. Pattern rules over SKILL.md and bundled files: known-bad commands, exfiltration URLs, secrets, obfuscation.
Behavioral analyzer. Checks what the skill asks the agent to do against what its description claims it does.
Llm analyzer. A language model reads the skill and reports intent-level issues the rules cannot express.
Trigger analyzer. Looks for instructions that fire on conditions the user did not ask for.
Meta analyzer. A second model pass that validates, deduplicates and re-scores the other analyzers' findings.

What we did not check

Runtime behaviour. The skill was not executed; findings come from reading its files.
Anything fetched at install or run time, including remote scripts, package dependencies, and URLs the skill tells the agent to open.
Content the analyzers cannot read: images, binaries, and some non-English text.
Known scanner bypass classes. See the methodology and limitations page.

Sources

Repository: https://github.com/jthack/ffuf_claude_skill
Raw scan result: ffuf-skill-scan.json
Badge for your README: ![skillscan.io](https://skillscan.io/badge/jthack-ffuf-web-fuzzing.svg)
Request a re-scan