Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add CALLE-AI/awesome-phone-call-agents --skill call-fraud-shieldgit clone --depth 1 https://github.com/CALLE-AI/awesome-phone-call-agentsWrote 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/calle-ai/awesome-phone-call-agents/call-fraud-shield)<a href="https://agentmods.dev/skills/calle-ai/awesome-phone-call-agents/call-fraud-shield"><img src="https://agentmods.dev/badge/skills/calle-ai/awesome-phone-call-agents/call-fraud-shield/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/calle-ai/awesome-phone-call-agents/call-fraud-shield"><img src="https://agentmods.dev/badge/skills/calle-ai/awesome-phone-call-agents/call-fraud-shield.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 | $0.00117 | $0.02635 |
| Opus 5.5 | $0.00047 | $0.01054 |
| Sonnet 5.5 | $0.00023 | $0.00527 |
| Haiku 4.5 | $0.00012 | $0.00264 |
Grade C, and why
call-fraud-shield scanned grade C with 1 finding 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 1mo 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.
Harvests environment variableshighData exfiltration
Enumerating or grepping the environment for keys collects credentials unrelated to what the mod says it does.
Stop vishing, spam, and scam calls before they extract credentials or money. How it starts
The opening of the file, as written. The whole thing — 280 lines — stays where its author put it; the contents beside it link to each section on GitHub.
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)
- Trajectory analysis — escalation-density scoring across call halves
- Scam archetype library — 8 documented scam patterns with harm trajectories
- XAI evidence spans — per-signal evidence text plus a readable explanation
- Mandatory false-positive disclaimer in every risk card
Scientific Foundation
| Research | Relevance |
|---|---|
| "It Warned Me Just at the Right Moment" arXiv:2502.03964 (CHI EA 2025) | Real-time vishing detection; motivates trajectory-over-single-turn analysis |
| Vishing-Tactics-Bench arXiv:2609.07151 (2026) | Situation-awareness benchmark; harm-projection field design |
| Talking Like a Phisher arXiv:2507.16291 (2025) | Adversarial transcripts evade keyword classifiers — justifies low-confidence labelling for keyword heuristics |
| VishGPT (MIS Quarterly, 2025) | RL-tuned large audio model for vishing detection; reference architecture for a future model-assisted extension |
What ships with it
8 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.
- references/example-transcript.json 1.2 KB
- references/examples.md 3.7 KB
- references/research-papers.md 2.1 KB
- references/safety.md 2.7 KB
- references/scam-archetypes.json 4.4 KB
- scripts/detect_fraud.py 15 KB runs code
- scripts/test_fraud_shield.py 33 KB runs code
- scripts/validate_risk_card.py 3.9 KB runs code
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.
- 1mo ago First seen · 280 lines · 117 tokens per session scan C 8fd0c03870a4
call-fraud-shield is a skill published in the GitHub repository CALLE-AI/awesome-phone-call-agents (109 stars, last pushed yesterday), licensed MIT. It adds 117 tokens to every session and 2,635 once invoked, about $0.0005 per session on Opus 5.5. A static security scan graded it C with 1 finding (harvests environment variables). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-18.
Other skills, from other repositories
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…
next-cache-components-optimizer
Optimize the meaningful UI available immediately from a Next.js route on an initial load (hard navigation) or named client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route and entry point at a time; the shipped test then guards…