Home / calle-ai / awesome-phone-call-agents · GitHub

call-fraud-shield SKILL.md skillA

call-fraud-shield from calle-ai/awesome-phone-call-agents is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.

Install it, pinned

mdr add calle-ai/awesome-phone-call-agents/call-fraud-shield@git:20260917.935f005

Pins git:20260917.935f005 in mdr.lock. Pin the fingerprint instead.

Audit grade: A, 17 of 17 checks passed
Kind: SKILL.md skill
Repository: calle-ai/awesome-phone-call-agents
Path: skills/call-fraud-shield/SKILL.md
Versions recorded: 1
Latest version: git:20260917.935f005, committed Sep 17, 2026
Size: 10,994 bytes
Repository stars: 112
License: MIT

Post-call fraud detection skill. Analyses a CALL-E transcript for vishing, spam, social engineering, and scam-script patterns using conversational trajectory analysis and a curated scam archetype library. Returns a structured risk card with XAI-explained evidence spans, threat category classification, an escalation-direction assessment, and a recommended action. Grounded in peer-reviewed vishing-detection and adversarial-evasion research (arXiv:2502.03964, arXiv:2609.07151, arXiv:2507.16291).

Collected from public GitHub. Every version is saved exactly as it was and never changes. Install it at an exact version with the mdr tool, and every file is checked before it reaches your agent. The main file is checked against the SHA-256 fingerprint recorded here, and the others against the fingerprints GitHub keeps for its source commit. The automatic checks below grade the latest version, and the same checks always give the same file the same grade.

What the file says

# call-fraud-shield

> **Detect fraud from the transcript — before the damage compounds.**

Stop vishing, spam, and scam calls before they extract credentials or money.
This skill analyses a call transcript for multi-layered fraud signals —
urgency language, authority impersonation, credential extraction attempts,
fear induction, and scam-script patterns — then returns a structured risk
card with a human-readable explanation and a clear recommended action.

---

## Why This Skill Exists

Traditional keyword-filter fraud detection is fragile: sophisticated social
engineering avoids blacklisted words. This skill takes a research-backed
*trajectory analysis* approach — tracking how threat-signal density *escalates*
over the course of a call — which is harder to evade with rephrased or
LLM-generated vishing scripts than fixed keyword lists.

The analysis runs in **heuristic mode only** (labelled `analysis_mode: "heuristic"`
in every output): pattern libraries, archetype matching, and trajectory
aggregation, with no external model call. What sets it apart from a plain
keyword screener:

- **4-category threat taxonomy** (SPAM, VISHING, SOCIAL_ENGINEERING, SCAM_SCRIPT)
…

Read the whole file at its exact version.

How to install

The exact contents, by fingerprint

mdr add calle-ai/awesome-phone-call-agents/call-fraud-shield@sha256:8fd0c03870a4f917

The line at the top of this page pins the label git:20260917.935f005, which is what most people want. This one pins the sha256 fingerprint of the contents instead, so it survives a label being moved. Either way the exact version is written to mdr.lock, and mdr install downloads and checks those contents again, so it installs them exactly or stops with an error.

Badge

[![mdr](https://markdownregistry.com/badge/art_3ggzojecdyztr4ja.svg)](https://markdownregistry.com/a/art_3ggzojecdyztr4ja)

2 badge image fetches in 30 days. What the badge shows.

Versions

The registry has recorded 1 version of this file, committed on Sep 17, 2026.

version	committed	commit	size	audit
git:20260917.935f005 latest	2026-09-17	935f005	10,994 B	A	view

Audit of the latest version

A 17 of 17 checks passed. Fixed automatic checks with no AI involved, so the same checks give the same answer every run.

pass: Frontmatter block present
pass: Frontmatter declares a name
pass: Frontmatter declares a description
pass: Size between 200 bytes and 200 KB (10994 bytes)
pass: No zero-width or bidi control characters
pass: No instruction hidden inside an HTML comment
pass: No link to an exfiltration or paste host
pass: No credential-shaped string
pass: No instruction to send local credentials anywhere
pass: No text hidden with inline styles
pass: No prompt-injection phrasing
pass: No curl or wget piped into a shell
pass: No recursive delete of root, home or parent
pass: No instruction to read or print local credentials
pass: No base64 blob over 200 characters
pass: No link to a raw IP address
pass: No script tag

Source

GitHub

calle-ai/awesome-phone-call-agents · 112 stars · license MIT · pushed 2026-11-05 · branch main

API

GET https://markdownregistry.com/api/v1/artifacts/art_3ggzojecdyztr4ja
GET https://markdownregistry.com/api/v1/resolve?ref=calle-ai/awesome-phone-call-agents/call-fraud-shield
GET https://markdownregistry.com/api/v1/blob/8fd0c03870a4f917ed0be307712a74ed84f613074bd76419bf67ab3e20329a9b

Your AI assistant does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.

Guides: the SKILL.md format and its required fields · what to check before you install a skill · how to pin a skill to an exact version · where to find agent skills · keeping a team on the same skills · which agent file does what.