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 quillai-network/quillshield_skills --skill external-call-safetygit clone --depth 1 https://github.com/quillai-network/quillshield_skillsWrote 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/quillai-network/quillshield_skills/external-call-safety)<a href="https://agentmods.dev/skills/quillai-network/quillshield_skills/external-call-safety"><img src="https://agentmods.dev/badge/skills/quillai-network/quillshield_skills/external-call-safety/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/quillai-network/quillshield_skills/external-call-safety"><img src="https://agentmods.dev/badge/skills/quillai-network/quillshield_skills/external-call-safety.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 | $0.00099 | $0.02843 |
| Opus 5 | $0.00049 | $0.01422 |
| Sonnet 5 | $0.00020 | $0.00569 |
| Haiku 4.5 | $0.00010 | $0.00284 |
Grade A, and why
external-call-safety scanned grade A with 0 findings 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 12d 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.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 327 lines — stays where its author put it; the contents beside it link to each section on GitHub.
External Call Safety
Detect vulnerabilities arising from unsafe interactions with external contracts and non-standard token behaviors that break protocol assumptions. Covers OWASP SC06 (Unchecked External Calls) plus the entire "weird ERC20" problem space.
When to Use
- Auditing any contract that calls external contracts (token transfers, cross-contract interactions)
- Reviewing protocols that support arbitrary/user-supplied ERC20 tokens
- Analyzing ETH payment distribution logic (airdrops, reward distribution, refunds)
- Verifying low-level call safety (
call,delegatecall,staticcall) - When a protocol claims to support "any ERC20 token"
When NOT to Use
- Reentrancy-specific analysis (use reentrancy-pattern-analysis — though there is overlap)
- Oracle/price feed analysis (use oracle-flashloan-analysis)
- Pure access control review (use semantic-guard-analysis)
Part 1: External Call Safety
Vulnerability Class 1: Unchecked Return Values
Low-level calls (call, delegatecall, staticcall) return a boolean indicating success. If unchecked, failed calls are silently ignored.
// VULNERABLE: Return value not checked
function withdraw(uint256 amount) external {
balances[msg.sender] -= amount;
payable(msg.sender).call{value: amount}(""); // Can fail silently!
// User's balance decreased but ETH not sent
}
// SAFE: Check return value
function withdraw(uint256 amount) external {
balances[msg.sender] -= amount;
(bool success, ) = payable(msg.sender).call{value: amount}("");
require(success, "Transfer failed");
}
Detection Algorithm:
For each low-level call expression:
1. Is the return value captured? (bool success, bytes memory data) = ...
2. Is the success boolean checked? require(success) or if(!success) revert
3. If not captured or not checked → UNCHECKED RETURN VALUE
Severity:
- ETH transfer unchecked → CRITICAL (funds lost)
- Token operation unchecked → HIGH (state desync)
- Non-financial call unchecked → MEDIUM
What ships with it
2 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.
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.
- 12d ago First seen · 327 lines · 99 tokens per session scan A a32ce524bb6f
external-call-safety is a skill published in the GitHub repository quillai-network/quillshield_skills (121 stars, last pushed 5mo ago), licensed MIT. It adds 99 tokens to every session and 2,843 once invoked, about $0.0005 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
ansem-crypto
Use when evaluating crypto narratives, attention rotation, memecoin cycles, Solana-style ecosystem momentum, social distribution, and reflexive retail flows in an Ansem-style crypto market framework.
arthur-hayes-liquidity
Use when evaluating crypto markets through an Arthur Hayes-style liquidity lens: dollar liquidity, funding, risk appetite, cycle psychology, and macro-driven crypto positioning.
cobie-cycle-filter
Use when evaluating crypto decisions through a Cobie-style cycle filter: common-sense risk, narrative traps, leverage humility, and avoiding obvious stupid trades.
cryptocred-structure
Use when evaluating crypto charts through a CryptoCred-style structure lens: levels, confluence, market structure, risk definition, and educational technical process.
willy-woo-onchain
Use when evaluating Bitcoin and crypto cycles through a Willy Woo-style on-chain lens: holder behavior, realized value, supply dynamics, and on-chain demand.
prompt-proximity-architecture
Turn an approved measurement charter, ICPs, and buyer jobs into a budget-aware prompt coverage blueprint across proximity bands, aided status, information acts, journey states, roles, locales, evidence grades, partitions, and measurement lanes. Use before prompt wording to define required, optional, and prohibited…