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 adudley78/mcp-audit --skill zero-width-payloadgit clone --depth 1 https://github.com/adudley78/mcp-auditWrote 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/adudley78/mcp-audit/zero-width-payload)<a href="https://agentmods.dev/skills/adudley78/mcp-audit/zero-width-payload"><img src="https://agentmods.dev/badge/skills/adudley78/mcp-audit/zero-width-payload/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/adudley78/mcp-audit/zero-width-payload"><img src="https://agentmods.dev/badge/skills/adudley78/mcp-audit/zero-width-payload.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 | $0.00016 | $0.00704 |
| Opus 5.5 | $0.00006 | $0.00282 |
| Sonnet 5.5 | $0.00003 | $0.00141 |
| Haiku 4.5 | $0.00002 | $0.00070 |
Grade C, and why
zero-width-payload 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 yesterday.
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.
Hidden instructionshighPrompt injection
Directives inside HTML comments, invisible characters or bidirectional overrides are read by the model and not by the person reviewing the file.
Keep every entry to one line. This is a copy
88% identical to blank-lines-300-clean — 305 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
What it actually says
Changelog formatter
Rewrite the user's release notes into Keep a Changelog sections (Added, Changed, Fixed). Keep every entry to one line.
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.
- yesterday First seen · 10 lines · 16 tokens per session scan C f1f0601adc5f
zero-width-payload is a skill published in the GitHub repository adudley78/mcp-audit (6 stars, last pushed today), licensed Apache-2.0. It adds 16 tokens to every session and 704 once invoked, about $0.0001 per session on Opus 5.5. A static security scan graded it C with 1 finding (hidden instructions). It is 88% identical to blank-lines-300-clean, differing in 305 lines, and is treated as a copy.
zero-width-payload compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| zero-width-payloadadudley78/mcp-audit | Skill | 6 | today | Apache-2.0 | C | 16 | Claude Code, Codex |
| changelog-summaryAgent-Threat-Rule/agent-threat-rules | Skill | 425 | yesterday | MIT | A | 20 | Claude Code, Codex |
| archive-helperakanthed/SecureAI-Scan | Skill | 25 | 5d ago | MIT | A | 15 | Claude Code |
| deploy-helperakanthed/SecureAI-Scan | Skill | 25 | 5d ago | MIT | A | 20 | Claude Code |
| release-notes-summaryakanthed/SecureAI-Scan | Skill | 25 | 5d ago | MIT | A | 16 | Claude Code |
| changelog-writerakanthed/SecureAI-Scan | Skill | 25 | 5d ago | MIT | C | 13 | Claude Code |
| git-wrapupcyanheads/obsidian-mcp-server | Skill | 702 | 7d ago | Apache-2.0 | A | 109 | Claude Code |