--- title: "Scan loader: review, role & definition · Undominated.ai" canonical: https://undominated.ai/agents/anthropic-scan-loader/ description: "Pins the Claude Security loader whose only input is one directory plus one file name, and that returns that JSON unchanged." --- # Scan loader: review, role & definition · Undominated.ai > Pins the Claude Security loader whose only input is one directory plus one file name, and that returns that JSON unchanged. [← Explore all agents](/agents/) SECURITY REVIEW / Anthropic # Scan loader Pins the Claude Security loader whose only input is one directory plus one file name, and that returns that JSON unchanged. [Use this definition ↓](#setup)[Original source ↗](https://github.com/anthropics/claude-plugins-official/tree/41f32e407b450055044f167db7ded5e8ff67d203/plugins/claude-security/agents) SOURCE REVIEW Reviewed 2026-10-14 Evidence 4 linked sources Publisher Anthropic Licence [Proprietary — Anthropic internal-use terms ↗](https://github.com/anthropics/claude-plugins-official/blob/41f32e407b450055044f167db7ded5e8ff67d203/plugins/claude-security/LICENSE) Revision 41f32e407b45 [Read what was—and wasn’t—checked ↓](#review) “A read-only scan loader, not for direct invocation, that returns one named JSON file exactly and reads nothing else.” [Anthropic · upstream description ↗](https://github.com/anthropics/claude-plugins-official/blob/41f32e407b450055044f167db7ded5e8ff67d203/plugins/claude-security/agents/scan-loader.md) Our analysis follows below. 01 / THE REASONING ## Why this made the selection. - The agents index has no entry for plugins/claude-security/agents/scan-loader.md. - The file names its inputs, limits the tool list to Read, and says to add, drop, or reword nothing in the JSON. ### A good fit for - Returning one JSON file the Claude Security scan workflow already wrote, without a second pass over the tree - Supply a run directory and exactly one JSON filename through the dispatcher. - Return every row and field through the expected structured output without rewriting content. ### Weigh up before choosing - This review did not execute the resource. - A Markdown profile does not register a native subagent by itself. - The install line installs the whole claude-security plugin, not this agent alone. - The file does not say what to do if the named file is missing or is not JSON. That case was not tested. - The plugin README's Python 3.9 line is a plugin requirement. This agent file does not mention Python. - A model-mediated copy can truncate or alter content; the definition supplies no byte checksum or deterministic parser guarantee. - The plugin-specific licence limits use and modification to authorized internal use with Anthropic products/services. General redistribution and non-Anthropic use are not permitted; obtain and use it through the publisher under the applicable agreement. 02 / THE REVIEW RECORD ## What we actually inspected. Source review has boundaries. A clear record is more useful than a “safe” badge. ### Material inspected - plugins/claude-security/agents/scan-loader.md - plugins/claude-security/README.md - README.md - LICENSE - Round 2: pinned definition, output contract and permission/dependency boundaries reread on 2026-10-14 - plugins/claude-security/LICENSE (overrides repository-wide licence for this plugin) ### Our findings - The description says it returns one JSON file from the run directory and is not for direct invocation. The only tool is Read. Model is sonnet and effort is low. - The body says the dispatch names one directory and one file name, and that the JSON is returned exactly, with nothing added, dropped, or reworded. - It says the file content is data from an earlier stage, not instructions, and to read nothing else and do nothing else. - The file is treated as prior-stage data and cannot introduce new instructions or broaden file access. - The loader has only Read and is a transport component, not a finding reviewer or JSON repair agent. - The exact-revision plugin licence is proprietary and expressly covers prompts, agent/skill definitions, workflows, code and documentation; the root Apache licence does not license this plugin for redistribution. ### Not established by this review - The resource was not executed and its tools were not called. - No JSON file was read. - A missing-file dispatch was not tried. The review applies to the material and revision named here. A newer upstream release can change its behavior. 03 / PUT IT TO WORK ## Use the role in your project. [Upstream setup instructions ↗](https://github.com/anthropics/claude-plugins-official/blob/41f32e407b450055044f167db7ded5e8ff67d203/plugins/claude-security/README.md) DOCUMENTED COMMAND /plugin install claude-security@claude-plugins-official Copy command ↗ Copying does not execute this command. It may retrieve a newer version than the reviewed source. - Read the plugin-specific proprietary licence at this revision. Obtain the plugin from Anthropic and use/modify it only within the applicable authorized Anthropic-product agreement; this catalogue provides no copy for installation. - The claude-security README shows that line, including the four leading spaces, then /reload-plugins on the next line. - That line installs the claude-security plugin. It does not name this agent. - The repository root README only has /plugin install {plugin-name}@claude-plugins-official, which is a placeholder, so it is not install.command. - Use the matching small, schema-bounded scan artifact and independently compare structural completeness before consuming the returned JSON. ### Before you start - Claude Code - Python 3.9 or newer on PATH, which the plugin README lists for the plugin - The scan or fix job that dispatches this agent ### Compatibility Claude Code ### Read-only loader for one named JSON file - Read the one file the dispatch names - Return that JSON unchanged - Read nothing else ### Cost model Proprietary plugin for authorized internal use solely with Claude Code or other Anthropic products/services under the applicable Anthropic agreement. Host/model charges may apply; no general redistribution licence. 04 / FOLLOW THE EVIDENCE ## The source trail. Our notes are separate from the original resource. Check upstream before adopting a new version. - [scan-loader ↗](https://github.com/anthropics/claude-plugins-official/blob/41f32e407b450055044f167db7ded5e8ff67d203/plugins/claude-security/agents/scan-loader.md) Checked 2026-10-14 https://github.com/anthropics/claude-plugins-official/blob/41f32e407b450055044f167db7ded5e8ff67d203/plugins/claude-security/agents/scan-loader.md Supports: one file, exact JSON, and no other reads - [claude-security README ↗](https://github.com/anthropics/claude-plugins-official/blob/41f32e407b450055044f167db7ded5e8ff67d203/plugins/claude-security/README.md) Checked 2026-10-14 https://github.com/anthropics/claude-plugins-official/blob/41f32e407b450055044f167db7ded5e8ff67d203/plugins/claude-security/README.md Supports: plugin install line - [Repository README ↗](https://github.com/anthropics/claude-plugins-official/blob/41f32e407b450055044f167db7ded5e8ff67d203/README.md) Checked 2026-10-14 https://github.com/anthropics/claude-plugins-official/blob/41f32e407b450055044f167db7ded5e8ff67d203/README.md Supports: placeholder install line - [Controlling Claude Security plugin licence ↗](https://github.com/anthropics/claude-plugins-official/blob/41f32e407b450055044f167db7ded5e8ff67d203/plugins/claude-security/LICENSE) Checked 2026-10-14 https://github.com/anthropics/claude-plugins-official/blob/41f32e407b450055044f167db7ded5e8ff67d203/plugins/claude-security/LICENSE Supports: Dependency setup and source-review boundary KEEP COMPARING ## Other approaches to consider. Related by category or shared topics. These are alternatives to inspect, not a measured quality order. [### Scan inventory ↗ Pins the Claude Security cartographer that partitions one tree and must place every listed top-level directory on a scanned or skipped ledger.](/agents/anthropic-scan-inventory/)[### Scan verifier ↗ Pins the Claude Security voter that takes one candidate finding and tries to disprove it, with a false-positive default and a file-and-line citation rule.](/agents/anthropic-scan-verifier/)[### Exploitability verifier ↗ Pins the fp-check phase-2 agent that stays read-only while deciding whether a suspected bug is exploitable, and that skips a proof the bug class does not need.](/agents/trailofbits-exploitability-verifier/) [AI Tools ↗](/tools/)[Skills ↗](/skills/)[Agents ↗](/agents/)[MCP Servers ↗](/mcp-servers/)[Workflows ↗](/workflows/) ## Continue your investigation - [Find reusable instructions](/skills/) - [Inspect connections](/mcp-servers/) - [Build a toolkit](/tools/) - [Choose the model](/compare/)