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 testing-llm-insecure-output-handlinggit 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/testing-llm-insecure-output-handling)<a href="https://agentmods.dev/skills/unboundcompute/security-agent-skills/testing-llm-insecure-output-handling"><img src="https://agentmods.dev/badge/skills/unboundcompute/security-agent-skills/testing-llm-insecure-output-handling/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/testing-llm-insecure-output-handling"><img src="https://agentmods.dev/badge/skills/unboundcompute/security-agent-skills/testing-llm-insecure-output-handling.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 | $0.00123 | $0.01575 |
| Opus 5.5 | $0.00049 | $0.00630 |
| Sonnet 5.5 | $0.00025 | $0.00315 |
| Haiku 4.5 | $0.00012 | $0.00158 |
Grade A, and why
testing-llm-insecure-output-handling 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 — 131 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Testing LLM insecure output handling: the output is the other half
Most LLM security attention is on the input. The output is the other half. An application that treats model output as safe and renders or executes it inherits an injection primitive, because the model can be steered (by a user or by poisoned content) into emitting exactly the payload the downstream sink will trust. The model becomes a confused deputy that writes the attacker's markup, escape sequence, or query, and the app runs it.
When to use
- The app renders model output as HTML or markdown in a browser.
- The output is printed to a terminal, written to logs, or shown in a CLI agent.
- Model output is concatenated into a shell command, a SQL query, a file path, or code that gets executed.
- Output is forwarded to another tool, agent, or stored and later displayed.
Scope check
Test outputs and sinks you own or are authorized to test. Use benign canary payloads and observe your own instrumentation; never exfiltrate real data. If you can't name the authorization, stop.
The loop
-
Trace every sink model output flows into. Follow the output from the model to where it lands: rendered as HTML or markdown, printed to a terminal, concatenated into a shell command or SQL, written to a file or log, fed to another tool or agent, stored and later displayed. Each is a sink that may trust the text.
-
Classify each sink's escaping. For each, ask what the sink executes and whether output is neutralized before it arrives: is HTML escaped, is markdown sanitized, are terminal escapes stripped, is the query parameterized, is the value quoted. An unescaped sink is where model output becomes code.
-
Test browser sinks. If output renders as HTML or markdown, get the model to emit a script or event-handler payload, or an image or link whose URL carries data, for example
. A rendered image with an attacker URL exfiltrates whatever the model puts in the query string, with no click. Markdown links and raw HTML both apply.
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 · 131 lines · 123 tokens per session scan A 2589c2b79e9d
testing-llm-insecure-output-handling is a skill published in the GitHub repository UnboundCompute/security-agent-skills (5 stars, last pushed 1mo ago), licensed MIT. It adds 123 tokens to every session and 1,575 once invoked, about $0.0005 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.