Skills verification-hygiene
📦

verification-hygiene

Content revision r1 High Risk ⚙️ External commands

Verify External Evidence with Source Discipline

Unstructured web search can turn stale or repeated claims into false confidence. This skill routes verification through target types, source tiers, freshness checks, and abstention rules.

Supports: Claude Codex Code(CC)
⚠️ 38 Poor

Install with my Agent

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

Agent request
Review the Skillstore skill "verification-hygiene" from https://skillstore.io/skills/syntagmanull-verification-hygiene.md and its manifest at https://skillstore.io/api/skills/syntagmanull-verification-hygiene/manifest. Verify the artifact. Stop and obtain explicit user consent before installing or changing files.

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/syntagmanull-verification-hygiene.md Signed manifest GET /api/skills/syntagmanull-verification-hygiene/manifest Signed lockfile GET /api/skills/syntagmanull-verification-hygiene/lockfile

Test it

Using "verification-hygiene". A user asks whether a platform policy changed this week.

Expected outcome:

The response identifies a status target, uses the latest official policy page, and marks older summaries as secondary context.

Using "verification-hygiene". A user repeats a viral quote attributed to a public figure.

Expected outcome:

The response traces the quote origin, notes repeated sources, and marks the claim unresolved when no primary record appears.

Using "verification-hygiene". A user asks why a company intentionally caused a market event.

Expected outcome:

The response removes the loaded premise, searches neutral event facts, and separates evidence from motive claims.

Security Audit

High Risk
v4 • 7/7/2026 Open versioned report

The static Ruby backtick and system reconnaissance findings are false positives caused by Markdown inline code and fact-checking examples. One semantic concern remains: the skill claims controlled-trial approval without verifiable marketplace attestation. No executable code, shell commands, network endpoints, or data exfiltration instructions were found in SKILL.md.

1
Files scanned
275
Lines analyzed
0
Review items
0
False positives ignored

Confirmed security concerns (1)

High
SKILL.md:23
Prompt Injection Attempt Detected
SKILL.md claims "Approved for controlled trial" without external attestation. This could bias marketplace or agent trust decisions.
The approval claim is explicit and appears in the untrusted skill text. It does not order reviewers to skip analysis, so intent is plausible but not certain.

Risk Factors

⚙️ External commands (51)
SKILL.md:12 SKILL.md:28 SKILL.md:30 SKILL.md:32 SKILL.md:34 SKILL.md:36 SKILL.md:39 SKILL.md:45 SKILL.md:47 SKILL.md:49 SKILL.md:51 SKILL.md:53 SKILL.md:55 SKILL.md:57 SKILL.md:76 SKILL.md:86 SKILL.md:88 SKILL.md:99 SKILL.md:106 SKILL.md:108 SKILL.md:110 SKILL.md:112 SKILL.md:136 SKILL.md:154 SKILL.md:158 SKILL.md:162 SKILL.md:164 SKILL.md:168 SKILL.md:170 SKILL.md:172 SKILL.md:174 SKILL.md:176 SKILL.md:178 SKILL.md:180 SKILL.md:182 SKILL.md:184 SKILL.md:197 SKILL.md:199 SKILL.md:201 SKILL.md:210 SKILL.md:218 SKILL.md:220 SKILL.md:222 SKILL.md:229 SKILL.md:231 SKILL.md:242 SKILL.md:251 SKILL.md:258 SKILL.md:260 SKILL.md:267 SKILL.md:269
Audited by: codex View Audit History →
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/syntagmanull-verification-hygiene/audits/4?utm_source=security_passport&utm_medium=share&utm_campaign=versioned_report

Markdown badge

[![Skillstore security assessment](https://skillstore.io/badges/skills/syntagmanull-verification-hygiene/security.svg)](https://skillstore.io/skills/syntagmanull-verification-hygiene?utm_source=security_passport_badge)

HTML badge

<a href="https://skillstore.io/skills/syntagmanull-verification-hygiene?utm_source=security_passport_badge"><img src="https://skillstore.io/badges/skills/syntagmanull-verification-hygiene/security.svg" alt="Skillstore security assessment" loading="lazy"></a>

Embed card

<iframe src="https://skillstore.io/embed/skills/syntagmanull-verification-hygiene.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

SyntagmaNull. (2026). verification-hygiene security audit report (audit version 4) [Author version unspecified]. Skillstore. https://skillstore.io/skills/syntagmanull-verification-hygiene/audits/4

BibTeX citation

@techreport{syntagmanull-syntagmanull-verification-hygiene-2026, author = {SyntagmaNull}, title = {verification-hygiene security audit report (audit version 4)}, institution = {Skillstore}, year = {2026}, number = {4}, url = {https://skillstore.io/skills/syntagmanull-verification-hygiene/audits/4}, 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: "verification-hygiene security audit report (audit version 4)" version: "unspecified" type: report authors: - name: "SyntagmaNull" date-released: "2026-07-07" url: "https://skillstore.io/skills/syntagmanull-verification-hygiene/audits/4" identifiers: - type: other value: "skillstore:syntagmanull-verification-hygiene:audit:4" description: "Skillstore immutable audit report identifier"

Skillstore Score

Why this score Evidence Confidence: Medium
55
Architecture
85
Maintainability
87
Content
69
Community
83
Spec Compliance

What You Can Build

Check Current Rules

Verify whether a policy, law, product feature, or platform rule is current before answering.

Trace Viral Claims

Find the source, date, and original context for quotes, screenshots, videos, or social claims.

Reduce Search Bias

Convert loaded prompts into neutral and disconfirming searches before forming a conclusion.

Try These Prompts

Verify a Simple Claim 
Use verification hygiene to check this claim. Identify the target type, choose authoritative sources, and state whether the claim is supported.
Check Current Status 
Use verification hygiene for a status question. Prefer current official sources and mark freshness as current, outdated, or unknown.
Trace Source Provenance 
Use verification hygiene to trace this claim to its earliest reliable source. Separate origin evidence from repeated commentary.
Resolve Conflicting Evidence 
Use verification hygiene to compare these conflicting sources. Test independence, map disagreements, and decide whether to support, contradict, or abstain.

Best Practices

  • Classify the verification target before searching.
  • Prefer primary sources when the answer depends on current rules, metrics, or official actions.
  • Use abstention when only tertiary or repeated sources are available.

Avoid

  • Do not copy the user premise into a search query without neutralizing it.
  • Do not count repeated articles as independent evidence.
  • Do not turn public sentiment into factual proof.

Frequently Asked Questions

Does this skill browse the web automatically?
No. It tells the host model how to route and evaluate searches when search tools are available.
What sources does it prefer?
It prefers official databases, court records, original media, policy pages, and primary research when those sources fit the claim.
How does it handle conflicting sources?
It maps the disagreement, checks whether sources are independent, and lowers confidence when the conflict remains unresolved.
Can it answer medical or legal questions?
It can guide evidence checks, but high stakes answers still require current authoritative sources and careful domain review.
Why does it use disconfirming searches?
Disconfirming searches reduce confirmation bias and help detect loaded user premises.
Is it ready for general deployment?
The source document says it is not approved for general deployment, so teams should review it before production use.

Developer Details

License

MIT

Skillstore revision

r1

Version notice

The author did not declare a version.

Repository

https://github.com/SyntagmaNull/judgment-hygiene-stack/tree/main/verification_hygiene

Ref

36e07d5e13068e5be64447e8f20b427cf2cbd21a

Maintenance freshness

7/18/2026

Usage

15 downloads · 129 views

File structure

📄 SKILL.md