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 UnboundCompute/security-agent-skills --skill hunting-unsafe-archive-extractiongit clone --depth 1 https://github.com/UnboundCompute/security-agent-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/unboundcompute/security-agent-skills/hunting-unsafe-archive-extraction)<a href="https://agentmods.dev/skills/unboundcompute/security-agent-skills/hunting-unsafe-archive-extraction"><img src="https://agentmods.dev/badge/skills/unboundcompute/security-agent-skills/hunting-unsafe-archive-extraction/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/unboundcompute/security-agent-skills/hunting-unsafe-archive-extraction"><img src="https://agentmods.dev/badge/skills/unboundcompute/security-agent-skills/hunting-unsafe-archive-extraction.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 | $0.00176 | $0.01968 |
| Opus 5.5 | $0.00070 | $0.00787 |
| Sonnet 5.5 | $0.00035 | $0.00394 |
| Haiku 4.5 | $0.00018 | $0.00197 |
Grade A, and why
hunting-unsafe-archive-extraction 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 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.
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 — 134 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Hunting unsafe archive extraction: when unpacking a file writes outside the box
Extracting an archive feels like a read, but it is a series of attacker-directed writes. Each entry carries a name, sometimes a link target, and a declared size, and a naive extractor trusts all three: it joins the name to the destination and writes, follows a link, and allocates whatever the entry claims. A crafted archive uses that trust to write outside the destination with a traversal path or a symlink, to overwrite a file that matters, or to expand a few kilobytes into enough data to exhaust disk or memory. You find these by tracing each entry's path, link, and size to the write it drives and asking what confirms the write stays inside and stays bounded.
When to use
- Code extracts a user-supplied or externally fetched archive to disk (import, restore, install, upload).
- Entry paths, symlinks, or declared sizes from the archive are trusted while writing.
- A written file is later executed, served, loaded, or read back as configuration.
Scope check
Unpack crafted archives only into systems and paths you own or are authorized to test, and in a sandbox where a write outside the destination cannot damage anything real. A path-escape proof can overwrite live files. If you can't name the authorization, stop.
The loop
-
Map where untrusted archives are extracted. Inventory the code paths that unpack a compressed archive whose contents come from a user or a remote source. Note the intended destination directory for each and whether the same routine handles nested archives. These extraction points are where an entry's metadata becomes a filesystem operation.
-
Trace each entry path to its write destination. For every entry, follow how its declared name is turned into a path and written. If the name is joined to the destination without normalizing it and confirming the result is still inside, a
../sequence or an absolute path writes outside the destination. The check has to be on the final resolved path, not on the raw name.
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 · 134 lines · 176 tokens per session scan A de55c50c3668
hunting-unsafe-archive-extraction is a skill published in the GitHub repository UnboundCompute/security-agent-skills (5 stars, last pushed 1mo ago), licensed MIT. It adds 176 tokens to every session and 1,968 once invoked, about $0.0007 per session on Opus 5.5. 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 2026-09-05.
Other skills, from other repositories
prodcheck-review
Review this codebase against the prodcheck pre-production checklists — security, performance, scale, integrations, post-launch readiness and people. Use when asked to check whether a project is ready to ship, to audit an area before launch, or to work through a specific checklist. Produces evidence with file:line…
integrate-arcjet-guard-genkit
Integrate Arcjet security into a Genkit JS agent using @arcjet/guard — wrap ai.defineTool, put guardMiddleware on generate({ use }) for unwrapped / MCP / filesystem tools, and read a caller-owned id from generate({ context }). Use when asked to add Arcjet to genkit, rate limit its tools, screen inbound messages, or…
integrate-arcjet-guard-tanstack-ai
Integrate Arcjet security into a TanStack AI chat() app using @arcjet/guard — put guardMiddleware first on chat({ middleware }) so onBeforeToolCall gates tools, and read a caller-owned id from chat({ context }). Use when asked to add Arcjet to TanStack AI, rate limit its tools, screen inbound messages, or block prompt…
integrate-arcjet-guard-claude-managed-agents
Integrate Arcjet security into Claude Managed Agents (hosted REST+SSE, beta managed-agents-2026-04-01) using @arcjet/guard — screen user.message / initialevents before sessions.events.send, and gate custom tools on agent.customtooluse. Use when asked to add Arcjet to Claude Managed Agents, rate limit custom tools, or…
linear-claude-skill
Manage Linear issues, projects, and teams.
varlock-claude-skill
Secure environment variable management ensuring secrets are never exposed in Claude sessions, terminals, logs, or git commits.