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-directory-sync-trustgit 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-directory-sync-trust)<a href="https://agentmods.dev/skills/unboundcompute/security-agent-skills/auditing-directory-sync-trust"><img src="https://agentmods.dev/badge/skills/unboundcompute/security-agent-skills/auditing-directory-sync-trust/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-directory-sync-trust"><img src="https://agentmods.dev/badge/skills/unboundcompute/security-agent-skills/auditing-directory-sync-trust.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 | $0.00202 | $0.02428 |
| Opus 5.5 | $0.00081 | $0.00971 |
| Sonnet 5.5 | $0.00040 | $0.00486 |
| Haiku 4.5 | $0.00020 | $0.00243 |
Grade A, and why
auditing-directory-sync-trust 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 — 155 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Auditing directory sync trust: a bulk feed reshapes identity, so validate what it says before you apply it
Directory synchronization keeps an application's users, groups, and privileges in step with an external source, an LDAP directory, an HR system, an identity provider, another directory, by importing that source's records in bulk on a schedule or on events. That makes the sync feed a firehose of identity changes the application applies largely without a human in the loop, so whatever the source says about who is an admin, who belongs to which group, and which account is which becomes internal truth. When the application trusts source attributes it never validates, a group membership, a department, an is-admin-like flag, an email, then whoever can influence those attributes at the source sets internal privilege. When the sync connector authenticates with a broad or long-lived credential, that credential can read and reshape the entire directory. When an external group name is allowed to map onto a privileged internal group, an attacker who controls a source group name escalates. When accounts are created or matched by a spoofable key like email or external id, an attacker record merges into an existing identity. And when a deletion or suspension in the source does not propagate, departed users linger with access. The audit treats the feed as untrusted input, checks that every attribute that sets privilege or identity is validated, and confirms the connector is scoped and deletions propagate. You audit this by feeding shaped source records and watching what internal state they create.
When to use
- An external directory feed (LDAP, HR system, identity provider, or cross-directory sync) drives internal account, group, and privilege state in bulk.
- The sync may trust source attributes (group, department, admin flag, email) to set privilege or tenancy without validation, or map an external group onto a privileged internal one.
- Accounts may be matched by a spoofable key, the connector credential may be broad, or source deletions may not propagate.
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 · 155 lines · 202 tokens per session scan A 51397f67385f
auditing-directory-sync-trust is a skill published in the GitHub repository UnboundCompute/security-agent-skills (5 stars, last pushed 1mo ago), licensed MIT. It adds 202 tokens to every session and 2,428 once invoked, about $0.0008 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.