Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/ShulkwiSEC/bb-hugenpx agentmods add skills/shulkwisec/bb-huge/deepfake-detection-and-analysisWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/shulkwisec/bb-huge/deepfake-detection-and-analysis)<a href="https://agentmods.dev/skills/shulkwisec/bb-huge/deepfake-detection-and-analysis"><img src="https://agentmods.dev/badge/skills/shulkwisec/bb-huge/deepfake-detection-and-analysis/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/shulkwisec/bb-huge/deepfake-detection-and-analysis"><img src="https://agentmods.dev/badge/skills/shulkwisec/bb-huge/deepfake-detection-and-analysis.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00086 | $0.01940 |
| Opus 5 | $0.00043 | $0.00970 |
| Sonnet 5 | $0.00017 | $0.00388 |
| Haiku 4.5 | $0.00009 | $0.00194 |
Grade A, and why
deepfake-detection-and-analysis scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 6d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
Copies of this mod
1 near-identical copy found in the catalogue:
- deepfake-detection-and-analysis — 100% identical, 0 lines differ
How it starts
The opening of the file, as written. The whole thing — 203 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Deepfake Detection & Analysis
When to Use
- When verifying the authenticity of sensitive media (executives, political figures)
- During incident response for CEO impersonation / BEC scams using voice cloning
- When investigating disinformation or influence operations
- When training corporate teams on deepfake recognition
- When building defensive pipelines for media upload portals
Prerequisites
- Access to target AI/ML system or local model deployment for testing
- Python 3.9+ with relevant ML libraries (transformers, torch, openai)
- Understanding of LLM architecture and prompt processing pipelines
- Authorized scope and rules of engagement for AI red team testing
Workflow
Phase 1: Visual Artifact Inspection (Manual)
# Extract frames from video for detailed analysis
ffmpeg -i suspicious_video.mp4 -vf fps=1/1 out%04d.png
# Look for these common visual artifacts:
# 1. Blinking anomalies (too much, too little, unnatural eyelids)
# 2. Lighting/Shadow inconsistencies (face lighting differs from background)
# 3. Blurring or edge artifacts around the face perimeter (the "mask" line)
# 4. Unnatural teeth rendering (AI struggles with individual teeth)
# 5. Mismatched skin tones or unnatural smoothness
# 6. Glitches during rapid movement or hand occlusion (hands passing in front of face)
# 7. Asymmetrical reflections in the eyes
Phase 2: Metadata & Provenance Analysis
# Check EXIF and metadata for manipulation traces
exiftool suspicious_media.jpg
exiftool suspicious_video.mp4
# Look for:
# - Missing standard camera metadata (Make, Model)
# - Software signatures (e.g., Photoshop, AfterEffects, Stable Diffusion)
# - Mismatched timestamps (creation vs. modification)
# - Missing or altered GPS data
# Check for C2PA (Coalition for Content Provenance and Authenticity) manifests
# Many legitimate AI tools now embed watermarks or provenance data
# Search for the source media (Reverse Image Search)
# Provide the isolated face or background to Yandex/Google images
# to find the original unaltered source material
What ships with it
2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 6d ago First seen · 203 lines · 86 tokens per session scan A f0febb6528cc
deepfake-detection-and-analysis is a skill published in the GitHub repository ShulkwiSEC/bb-huge (22 stars, last pushed 2mo ago), licensed MIT. It adds 86 tokens to every session and 1,940 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.
Other skills, from other repositories
deepfake-detection-and-analysis
Analyze and detect synthetic media, including deepfake videos, AI-generated images, and cloned voice audio. Use this skill when investigating potential disinformation campaigns, verifying the authenticity of digital evidence, or assessing social engineering attacks leveraging synthetic media (e.g., vishing with voice…
analyzing-linux-system-artifacts
Examine Linux system artifacts (auth logs, cron/systemd persistence, shell history, SSH keys, and system configuration) to uncover evidence of compromise, detect rootkits or backdoors, and reconstruct user/attacker activity. Use when investigating a compromised Linux server or workstation, hunting for persistence…
analyzing-email-headers-for-phishing-investigation
Parse and analyze email headers (Received chain, Return-Path, Message-ID) to trace the true origin of a phishing email and validate SPF, DKIM, and DMARC results to confirm or rule out sender spoofing. Use when triaging a suspicious or reported email, investigating a phishing incident, or verifying whether a message's…
acquiring-disk-image-with-dd-and-dcfldd
Create forensically sound bit-for-bit disk images with dd or dcfldd on a Linux forensic workstation, preserving evidence integrity through hash verification (MD5/SHA) during acquisition. Use when imaging a suspect drive, USB device, or memory card for investigation, preserving volatile disk evidence during incident…
analyzing-linux-audit-logs-for-intrusion
Uses the Linux Audit framework (auditd) with ausearch and aureport utilities to detect intrusion attempts, unauthorized access, privilege escalation, and suspicious system activity. Covers audit rule configuration, log querying, timeline reconstruction, and integration with SIEM platforms. Activates for requests…
analyzing-linux-kernel-rootkits
Detect kernel-level rootkits in Linux memory dumps using Volatility3 linux plugins (checksyscall, lsmod, hiddenmodules), rkhunter system scanning, and /proc vs /sys discrepancy analysis to identify hooked syscalls, hidden kernel modules, and tampered system structures.