special-chars-skill

special-chars-skill is a skill for Claude Code, Codex from maxvaega/skillkit. It costs 15 tokens per session (186 once invoked), scanned B, original, MIT.

A test skill for checking how special characters and unsafe input are handled. It treats placeholders, shell symbols, markup, path traversal, and injection-like text as ordinary text.

In plain words
What is it for?
Use it when testing argument substitution and input handling for commands or skills that accept arbitrary text.
Why use it?
It helps verify that user input is not executed, interpreted as a command, or used to escape the intended folder or operation.

Skill for Claude CodeCodex

Install

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.

agentmods
npx agentmods add skills/maxvaega/skillkit/edge-special-chars
Any agent
npx skills add maxvaega/skillkit --skill edge-special-chars
Clone the repo
git clone --depth 1 https://github.com/maxvaega/skillkit

Made for: Claude Code, Codex.

Wrote 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.

agentmods badge for special-chars-skill

README.md
[![agentmods](https://agentmods.dev/badge/skills/maxvaega/skillkit/edge-special-chars.svg)](https://agentmods.dev/skills/maxvaega/skillkit/edge-special-chars)
Your own site
<a href="https://agentmods.dev/skills/maxvaega/skillkit/edge-special-chars"><img src="https://agentmods.dev/badge/skills/maxvaega/skillkit/edge-special-chars.svg" alt="Measured on agentmods" height="20"></a>
Per session 15 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 186 The whole file, excluding the scripts and references it only reads on demand.
Security scan B 1 finding. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00015 $0.00186
Opus 5 $0.00008 $0.00093
Sonnet 5 $0.00003 $0.00037
Haiku 4.5 $0.00002 $0.00019

Measured 5d ago against content hash 80862a45b03f, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade B, and why

special-chars-skill scanned grade B 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 5d 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.

Recursive force deletemediumDestructive command

rm -rf with a variable or a broad path is one typo away from removing the wrong tree.

- Command injection: ; rm -rf / ; $(whoami)

Downgraded: this mod is about security review, or the phrase is quoted, so it is likely naming the pattern rather than instructing it.

tests/fixtures/skills/edge-special-chars/SKILL.md · 30 lines

What it actually says

Special Characters Skill

This skill tests handling of special characters in $ARGUMENTS placeholder.

Test cases covered:

  • HTML/XML special chars: < > & " '
  • Shell metacharacters: $ ` ; | & ( ) [ ] { }
  • Path traversal attempts: ../ ../../etc/passwd
  • SQL injection patterns: ' OR '1'='1
  • Command injection: ; rm -rf / ; $(whoami)
  • Unicode and emoji: 你好 🎉 émoji

Usage: $ARGUMENTS

Expected Behavior

The ContentProcessor should safely substitute arguments without:

  1. Executing shell commands
  2. Interpreting special characters
  3. Allowing path traversal
  4. Enabling injection attacks

All input should be treated as literal text.

Changes

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.

  1. 5d ago First seen · 30 lines · 15 tokens per session scan B 80862a45b03f

Subscribe to this mod's changes

special-chars-skill is a skill published in the GitHub repository maxvaega/skillkit (147 stars, last pushed 7mo ago), licensed MIT. It adds 15 tokens to every session and 186 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it B with 1 finding (recursive force delete). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Related

Other skills, from other repositories