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-command-argument-and-flag-injectiongit 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-command-argument-and-flag-injection)<a href="https://agentmods.dev/skills/unboundcompute/security-agent-skills/hunting-command-argument-and-flag-injection"><img src="https://agentmods.dev/badge/skills/unboundcompute/security-agent-skills/hunting-command-argument-and-flag-injection/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-command-argument-and-flag-injection"><img src="https://agentmods.dev/badge/skills/unboundcompute/security-agent-skills/hunting-command-argument-and-flag-injection.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 | $0.00184 | $0.02070 |
| Opus 5.5 | $0.00074 | $0.00828 |
| Sonnet 5.5 | $0.00037 | $0.00414 |
| Haiku 4.5 | $0.00018 | $0.00207 |
Grade A, and why
hunting-command-argument-and-flag-injection 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 — 136 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Hunting command argument and flag injection: when a value becomes an option
Argument injection lives in the safe-looking case: a program is spawned without a shell, as a fixed binary with a separate argument vector, so there is no metacharacter interpretation and command injection does not apply. The bug is that the target program parses its own arguments, and an attacker-controlled value placed in the vector can be read as an option rather than as data. A value that begins with a dash becomes a flag; a value inserted where the program has not yet seen the options-terminator can turn on a behavior the caller never intended, writing to a file, reading one, executing an embedded command, changing an output or a protocol, or contacting a network host. Because there is no shell, defenses aimed at metacharacters do nothing. You find it by locating shell-less spawns whose argument vector includes untrusted values and asking whether the target can parse those values as options.
When to use
- Code spawns a fixed program with an argument vector (no shell) that includes untrusted input.
- The target program accepts options that read or write files, run commands, or change its destination.
- Input can start with a dash, or is inserted before a fixed set of trailing operands.
Scope check
Test argument injection only against systems you own or are authorized to assess, on non-production hosts, because a confirmed case makes a real tool take an unintended action. Prove the class with an inert option whose effect is observable but harmless, and stay within the authorized host. If you can't name the authorization, stop.
The loop
- Establish that input can occupy an option slot first. For each shell-less spawn, determine whether an
untrusted value can start with a dash, or be positioned in the vector before the program has seen an
options terminator, so the target parses it as an option rather than an operand. This is the
false-positive killer: a value pinned after a
--terminator, or in a fixed operand position the program treats as data, cannot become a flag. Confirm the value can reach an option-parsed slot before going on.
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 · 136 lines · 184 tokens per session scan A e530cdd21b7d
hunting-command-argument-and-flag-injection is a skill published in the GitHub repository UnboundCompute/security-agent-skills (5 stars, last pushed 1mo ago), licensed MIT. It adds 184 tokens to every session and 2,070 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.