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 auditing-error-handling-and-information-exposuregit 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/auditing-error-handling-and-information-exposure)<a href="https://agentmods.dev/skills/unboundcompute/security-agent-skills/auditing-error-handling-and-information-exposure"><img src="https://agentmods.dev/badge/skills/unboundcompute/security-agent-skills/auditing-error-handling-and-information-exposure/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/auditing-error-handling-and-information-exposure"><img src="https://agentmods.dev/badge/skills/unboundcompute/security-agent-skills/auditing-error-handling-and-information-exposure.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 | $0.00147 | $0.01933 |
| Opus 5.5 | $0.00059 | $0.00773 |
| Sonnet 5.5 | $0.00029 | $0.00387 |
| Haiku 4.5 | $0.00015 | $0.00193 |
Grade A, and why
auditing-error-handling-and-information-exposure 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 — 138 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Auditing error handling and information exposure: when a failure tells the attacker how it works
Every application fails, and how it fails is a message to whoever is probing it. A stack trace names the framework, the file layout, and the line that broke. A database error quotes the query and confirms an injection point. A verbose not-found versus a verbose forbidden tells an attacker which accounts exist. A debug endpoint left on in production hands over configuration and sometimes secrets. None of this is a memory-corruption bug or an injection; it is the system narrating its internals to an unauthenticated client, turning blind probing into informed attack. The audit is not about suppressing all errors; it is about deciding, for the deployed configuration, whether what a real client receives on failure reveals security-relevant structure. You find it by driving the error paths a client can reach and reading exactly what comes back.
When to use
- A service returns errors on malformed, unauthorized, or failing requests and you can observe the responses.
- Debug modes, verbose error pages, or diagnostic and health endpoints may be reachable in production.
- Build or deployment artifacts (source maps, version-control metadata, backups) may be served publicly.
Scope check
Test error and diagnostic surfaces only against systems you own or are authorized to assess, using benign malformed input rather than live exploitation to trigger failures, and treat any disclosed secret as a real credential to be reported and rotated, not reused. Stay within the authorized scope. If you can't name the authorization, stop.
The loop
- Establish what a real client receives in the deployed configuration first. Determine whether the production error handler is active and debug mode is off, so the verbose page you see locally is not what a client actually gets. This is the false-positive killer: a detailed trace visible only under a developer flag that is disabled in production is not a finding, while the generic page that production returns is the real evidence. Confirm the deployed behavior before judging the detail.
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 · 138 lines · 147 tokens per session scan A d1acf5c7fc74
auditing-error-handling-and-information-exposure is a skill published in the GitHub repository UnboundCompute/security-agent-skills (5 stars, last pushed 1mo ago), licensed MIT. It adds 147 tokens to every session and 1,933 once invoked, about $0.0006 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.