sharp-edges
Identifies error-prone APIs, dangerous configurations, and footgun designs that enable security mistakes. Use when reviewing API designs, configuration schemas, cryptographic library ergonomics, or evaluating whether code follows 'secure by
- License
- CC-BY-SA-4.0
- SKILL.md tokens
- 2,953
- Bundled files
- 18
- Bundled tokens (estimated)
- 29,678
Cost per 1,000 loads
Estimated input cost per 1,000 loads of SKILL.md only (characters ÷ 4). Bundled files, output tokens and execution are excluded.
| Model | Input / 1M tokens | 1,000 loads |
|---|---|---|
| Claude Opus 5 | $5.00 | $14.77 |
| Claude Sonnet 5 | $2.00 | $5.91 |
| Claude Haiku 4.5 | $1.00 | $2.95 |
Safety flags
Detected automatically from files; not a security audit.
- Runs scripts
- No
- Network access
- No
- Shell commands
- No
Works with
Open SKILL.md format
- Claude Code
- Codex
- Cursor
- GitHub Copilot
- Gemini CLI
- OpenCode
- Goose
Install
npx skills add trailofbits/skills --skill sharp-edgesLast verified:
sharp-edges FAQ
What does the sharp-edges skill do?
Identifies error-prone APIs, dangerous configurations, and footgun designs that enable security mistakes. Use when reviewing API designs, configuration schemas, cryptographic library ergonomics, or evaluating whether code follows 'secure by Source: https://github.com/trailofbits/skills/blob/main/plugins/sharp-edges/skills/sharp-edges/SKILL.md
What does the sharp-edges skill cost to load?
SKILL.md is about 2,953 tokens. Estimated input cost per 1,000 loads: Claude Opus 5 $14.77; Claude Sonnet 5 $5.91; Claude Haiku 4.5 $2.95. Estimated input cost per 1,000 loads of SKILL.md only (characters ÷ 4). Bundled files, output tokens and execution are excluded. Prices: https://docs.anthropic.com/en/docs/about-claude/pricing
How do I install the sharp-edges skill?
Skills CLI: npx skills add trailofbits/skills --skill sharp-edges. Claude Code: /plugin marketplace add trailofbits/skills, then install the plugin from that marketplace. Download the sharp-edges skill folder as a ZIP and upload it in Claude.ai skills settings.
Is the sharp-edges skill safe?
No runs-scripts, network-access or shell-command flags were detected. Flags are detected automatically from the skill's files and are not a security audit; review the SKILL.md before installing.