Skills sent-contacts
📦

sent-contacts

Content revision r1 Safe ⚙️ External commands

Manage Sent Contacts Safely

Contact searches, bulk imports, and deletions can expose private data or modify the wrong records. This skill applies scoped lookups, minimal disclosure, and confirmation gates.

Supports: Claude Codex Code(CC)
🥉 78 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 "sent-contacts" from https://skillstore.io/skills/sentdm-sent-contacts.md and its manifest at https://skillstore.io/api/skills/sentdm-sent-contacts/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/sentdm-sent-contacts.md Signed manifest GET /api/skills/sentdm-sent-contacts/manifest Signed lockfile GET /api/skills/sentdm-sent-contacts/lockfile

Test it

Using "sent-contacts". Find contacts named Priya and show only what I need to identify them.

Expected outcome:

Found two matching contacts. Contact ct_104 is Priya S. ending in 0182. Contact ct_221 is Priya N. ending in 7740.

Using "sent-contacts". Import these 25 contacts after removing duplicates.

Expected outcome:

  • Preview: 23 unique records and 2 duplicates removed.
  • Scope: organization North Region, Sender Profile Support.
  • No contacts have been created. Confirm this exact batch to continue.

Using "sent-contacts". Delete contact ct_104.

Expected outcome:

Delete preview: ct_104, Priya S., phone ending in 0182. This action is destructive. Confirm deletion of this exact contact.

Security Audit

Safe
v1 • 9/2/2026 Open versioned report

All 11 static findings are false positives caused by Markdown backticks around Sent MCP tool names, not Ruby or shell execution. The skill contains no executable commands, prompt injection, or other semantic security findings, and it requires explicit confirmation before mutations.

2
Files scanned
52
Lines analyzed
0
Review items
0
False positives ignored

Risk Factors

⚙️ External commands (11)
SKILL.md:8 SKILL.md:12 SKILL.md:18 SKILL.md:19 SKILL.md:20 SKILL.md:27 SKILL.md:30 SKILL.md:32 SKILL.md:37 SKILL.md:40 SKILL.md:42
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/sentdm-sent-contacts/audits/1?utm_source=security_passport&utm_medium=share&utm_campaign=versioned_report

Markdown badge

[![Skillstore security assessment](https://skillstore.io/badges/skills/sentdm-sent-contacts/security.svg)](https://skillstore.io/skills/sentdm-sent-contacts?utm_source=security_passport_badge)

HTML badge

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

Embed card

<iframe src="https://skillstore.io/embed/skills/sentdm-sent-contacts.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

sentdm. (2026). sent-contacts security audit report (audit version 1) [Author version unspecified]. Skillstore. https://skillstore.io/skills/sentdm-sent-contacts/audits/1

BibTeX citation

@techreport{sentdm-sentdm-sent-contacts-2026, author = {sentdm}, title = {sent-contacts security audit report (audit version 1)}, institution = {Skillstore}, year = {2026}, number = {1}, url = {https://skillstore.io/skills/sentdm-sent-contacts/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: "sent-contacts security audit report (audit version 1)" version: "unspecified" type: report authors: - name: "sentdm" date-released: "2026-09-02" url: "https://skillstore.io/skills/sentdm-sent-contacts/audits/1" identifiers: - type: other value: "skillstore:sentdm-sent-contacts:audit:1" description: "Skillstore immutable audit report identifier"

Skillstore Score

Why this score Evidence Confidence: Medium
55
Architecture
85
Maintainability
87
Content
65
Community
91
Spec Compliance

What You Can Build

Find a customer contact

Search a narrow contact set and retrieve the exact record needed for support.

Prepare a contact import

Validate, deduplicate, preview, and confirm a controlled batch before creation.

Remove an obsolete contact

Resolve, fetch, preview, and confirm one exact record before deletion.

Try These Prompts

Search contacts 
Find Sent contacts matching [name or phone fragment]. Return only identifiers, labels, and masked phone numbers.
Inspect one contact 
Retrieve contact [contact ID] and summarize only the fields needed for [task]. Include its messaging summary without inferring consent.
Prepare a bulk import 
Validate and deduplicate these contacts: [records]. Preview the exact batch, scope, duplicate handling, and masked targets before asking for confirmation.
Verify and delete a contact 
Resolve contact [identifier], fetch the exact record, and show a destructive-action preview. Ask for explicit confirmation immediately before deletion.

Best Practices

  • Use the narrowest filter and return only fields required for the task.
  • Verify the active organization and Sender Profile before every mutation.
  • Require a fresh preview and explicit confirmation for each create, delete, or retry.

Avoid

  • Do not expose tokens, credentials, authorization headers, or unnecessary contact data.
  • Do not treat messaging history or number presence as proof of consent.
  • Do not delete from guessed identifiers, broad filters, or stale results.

Frequently Asked Questions

Does this skill require a Sent account?
Yes. It requires an authorized Sent MCP connection using client-managed OAuth 2.1 and PKCE.
Can it search my entire contact book?
It can page through contacts, but it should use narrow filters and avoid unnecessary full exports.
Can it create many contacts at once?
Yes. It validates, deduplicates, previews, and requests explicit confirmation before creating the exact batch.
Can it delete contacts automatically?
No. It must fetch the exact contact, show a deletion preview, and receive fresh explicit confirmation.
Does a messaging summary prove consent?
No. Messaging history and number presence do not establish consent or current reachability.
What happens when a mutation result is unclear?
The skill reports uncertainty, avoids automatic retries, and rechecks the target before requesting another confirmation.

Developer Details

Author

sentdm

License

MIT

Skillstore revision

r1

Version notice

The author did not declare a version.

Repository

https://github.com/sentdm/sent-plugin/tree/bfc21e75db359a9c4022b4654055b04830342cbc/skills/sent-contacts

Ref

096c7daa4d0d974771dad12d81c3d0d4688617b9

Maintenance freshness

9/8/2026

Usage

0 downloads · 0 views

File structure

📁 agents/

📄 openai.yaml

📄 SKILL.md