Skills is-this-photo-real
📦

is-this-photo-real

Content revision r1 Safe ⚙️ External commands📁 Filesystem access🔑 Env variables

Verify Photo and Video Authenticity

Misleading media often pairs authentic pixels with false captions, while detector scores create false certainty. This skill prioritizes provenance, physical consistency, and transparent limits.

Supports: Claude Codex Code(CC)
🥉 77 Bronze

Install with my Agent

Copy this request to your Agent. It includes the canonical Skill page and manifest.

Agent request
Review the Skillstore skill "is-this-photo-real" from https://skillstore.io/skills/useosint-is-this-photo-real.md and its manifest at https://skillstore.io/api/skills/useosint-is-this-photo-real/manifest. Verify the artifact. You may proceed after verification, subject to the environment's own policy.

Your Agent should still show its plan and request any confirmation required by the security policy.

Agent-readable resources

Use these links when an AI agent, crawler, or script needs clean context instead of reading the full page.

Markdown detail GET /skills/useosint-is-this-photo-real.md Signed manifest GET /api/skills/useosint-is-this-photo-real/manifest Signed lockfile GET /api/skills/useosint-is-this-photo-real/lockfile

Test it

Using "is-this-photo-real". A social post says this explosion video was recorded today in City A.

Expected outcome:

  • Conclusion: confirmed recontextualized.
  • An archived news page published the same skyline footage eighteen months earlier in another country.
  • The available copy is a platform re-encode, so signal-level authenticity tests are invalid.
  • Audio may be edited because a hard cut aligns with a noise-floor change.

Using "is-this-photo-real". Determine whether this portrait is AI-generated.

Expected outcome:

  • Conclusion: unconfirmed.
  • No reliable provenance was found, but absence of provenance does not prove synthesis.
  • Lighting and perspective remain coherent, while small background text shows localized structural errors.
  • Obtain the original file and compare multiple independent indicators before reaching a stronger conclusion.

Using "is-this-photo-real". Check whether this screenshot proves the quoted account posted the message.

Expected outcome:

  • Conclusion: the screenshot alone cannot verify authorship.
  • Interface layout is plausible, but screenshots can be recreated without image-editing traces.
  • Verify the underlying post, archived captures, account history, and platform identifiers.

Security Audit

Safe
v1 • 8/3/2026 Open versioned report

All static findings are false positives from Markdown code formatting, ordinary forensic terminology, or a documentation link. No malicious intent, unsafe interpolation, prompt injection, or secret access was found.

3
Files scanned
677
Lines analyzed
0
Review items
0
False positives ignored

Risk Factors

⚙️ External commands (20)
SKILL.md:31 SKILL.md:47 SKILL.md:49 SKILL.md:51 SKILL.md:56 SKILL.md:145 SKILL.md:147 SKILL.md:162 SKILL.md:181 SKILL.md:209 SKILL.md:224 SKILL.md:235 SKILL.md:241 SKILL.md:242 SKILL.md:243 SKILL.md:244 SKILL.md:245 SKILL.md:246 SKILL.md:247 SKILL.md:248
📁 Filesystem access (1)
SKILL.md:259
🔑 Env variables (2)
SKILL.md:188 SKILL.md:200
No confirmed security findings were detected by the latest completed static and semantic audit. This does not prove the skill has no side effects.
Audited by: codex
Share & cite this report

Share the versioned assessment report, neutral badge, embed card, and citations. Skillstore reports evidence without deciding whether this Skill is safe.

Open versioned report
Security Assessment

Copy report link

https://skillstore.io/skills/useosint-is-this-photo-real/audits/1?utm_source=security_passport&utm_medium=share&utm_campaign=versioned_report

Markdown badge

[![Skillstore security assessment](https://skillstore.io/badges/skills/useosint-is-this-photo-real/security.svg)](https://skillstore.io/skills/useosint-is-this-photo-real?utm_source=security_passport_badge)

HTML badge

<a href="https://skillstore.io/skills/useosint-is-this-photo-real?utm_source=security_passport_badge"><img src="https://skillstore.io/badges/skills/useosint-is-this-photo-real/security.svg" alt="Skillstore security assessment" loading="lazy"></a>

Embed card

<iframe src="https://skillstore.io/embed/skills/useosint-is-this-photo-real.html" title="Skillstore Security Assessment" sandbox="allow-popups allow-popups-to-escape-sandbox" loading="lazy" referrerpolicy="no-referrer" width="420" height="180"></iframe>
Academic citations (APA · BibTeX · CFF)

APA citation

useosint. (2026). is-this-photo-real security audit report (audit version 1) [Author version unspecified]. Skillstore. https://skillstore.io/skills/useosint-is-this-photo-real/audits/1

BibTeX citation

@techreport{useosint-useosint-is-this-photo-real-2026, author = {useosint}, title = {is-this-photo-real security audit report (audit version 1)}, institution = {Skillstore}, year = {2026}, number = {1}, url = {https://skillstore.io/skills/useosint-is-this-photo-real/audits/1}, note = {Author version unspecified} }

CITATION.cff

cff-version: 1.2.0 message: "If you use this Skill, cite its author and this versioned security audit report." title: "is-this-photo-real security audit report (audit version 1)" version: "unspecified" type: report authors: - name: "useosint" date-released: "2026-08-03" url: "https://skillstore.io/skills/useosint-is-this-photo-real/audits/1" identifiers: - type: other value: "skillstore:useosint-is-this-photo-real:audit:1" description: "Skillstore immutable audit report identifier"

Skillstore Score

Why this score Evidence Confidence: Medium
55
Architecture
85
Maintainability
87
Content
65
Community
83
Spec Compliance

What You Can Build

Verify Breaking News Media

Trace earlier copies, compare captions, and test claimed locations before publishing or sharing.

Review Submitted Evidence

Assess provenance, processing history, and manipulation indicators in claims, onboarding, or evidence review.

Investigate Synthetic Media

Evaluate physical consistency, structural coherence, metadata, and detector limitations without relying on one score.

Try These Prompts

Check a Media Claim 
Assess [media] against this claim: [claim]. Start with provenance, identify the best copy, and report evidence, uncertainty, and invalid tests.
Trace Earlier Publication 
Verify whether [media] appeared earlier under another caption. Compare source dates, credits, archived pages, keyframes, and location clues.
Assess Manipulation 
Evaluate [file] for manipulation or synthesis. Classify its processing history, then assess metadata, geometry, lighting, compression, and durable structural indicators.
Test Competing Hypotheses 
Analyze [media] under authentic, recontextualized, manipulated, and synthetic hypotheses. Rank evidence, test alternatives, document assumptions, and define decisive follow-up evidence.

Best Practices

  • State the exact claim before testing and separate each conclusion by origin, caption, location, date, manipulation, and synthesis.
  • Obtain the least processed copy, record its source and history, hash it, and work on duplicates.
  • Document negative results, invalid tests, assumptions, and evidence that could change the conclusion.

Avoid

  • Do not label media fake from one detector score, heatmap, metadata field, or visual anomaly.
  • Do not run signal-level tests on screenshots or platform re-encodes without explaining why results are unreliable.
  • Do not upload sensitive, intimate, victim, or confidential media to services that retain or publish submissions.

Frequently Asked Questions

Can this skill prove a photo is real?
It can verify specific claims and evidence. It cannot prove every unseen aspect of authenticity.
Does missing metadata mean an image is fake?
No. Platforms and editing workflows often remove metadata, so absence is usually inconclusive.
Are AI-image detector scores reliable?
They are weak signals with false positives and false negatives. Never use one score as the conclusion.
Why does the workflow start with provenance?
Earlier copies and original captions often resolve false claims faster and more defensibly than pixel analysis.
Can it analyze video?
Yes. It covers keyframes, containers, encoders, frame behavior, audio consistency, provenance, and processing loss.
What is needed for the strongest assessment?
Provide the best available file, exact claim, source context, known processing history, and any original publication links.

Developer Details

Author

useosint

License

MIT

Skillstore revision

r1

Version notice

The author did not declare a version.

Repository

https://github.com/useosint/osint-skills/tree/06243a5620b0c9c97502edd4ee9e31995a3bdccd/skills/is-this-photo-real

Ref

76c3621ba67d9236f7e0674bbf2a2ecc2696e20c

Maintenance freshness

8/3/2026

Usage

0 downloads · 0 views

File structure

📁 reference/

📄 tool-catalogue.md

📄 verification-checklist.md

📄 SKILL.md