Answer: On each file edit, the plugin scans the new content for known risky patterns, including dynamic code execution, unsafe deserialization, DOM injection, and edits under workflow files. The check runs after the edit lands and appends the warning to Claude's context for the next step. Status: Confirmed Entry: tool/claude-code/permissions-and-security/security-plugin-file-edit-checks Revision: 2 Digest: sha256:76ceba481b0989f9 (changes whenever the content changes) Timeline: Created: 2026-11-13T03:05:36Z Last changed: 2026-11-19T12:20:00Z (custom patterns file: — → security-patterns.yaml) Last verified: 2026-11-20T12:24:44Z Next check: 2026-11-21T12:24:44Z Check interval: Daily Expected change: No fixed schedule Data: Field | Value | Source | As of check action | scans the new content for known risky patterns | [1] | 2026-11-20 dynamic code execution patterns | eval( | [1] | 2026-11-20 unsafe deserialization pattern | pickle | [1] | 2026-11-20 DOM injection patterns | dangerouslySetInnerHTML | [1] | 2026-11-20 workflow files path | .github/workflows/ | [1] | 2026-11-20 timing | after the edit lands | [1] | 2026-11-20 warning frequency | once per pattern per file per session | [1] | 2026-11-20 custom patterns file | security-patterns.yaml | [1] | 2026-11-20 Sources: [1] Anthropic. "Catch security issues as Claude writes code". https://code.claude.com/docs/en/security-guidance.md Role: primary. Accessed: 2026-11-20T12:24:44Z Quote: "the plugin scans the new content for known risky patterns" (Supports: check action) Quote: "Dynamic code execution: `eval(`, `new Function`, `os.system`, `child_process.exec`" (Supports: dynamic code execution patterns) Quote: "Unsafe deserialization: `pickle`" (Supports: unsafe deserialization pattern) Quote: "DOM injection: `dangerouslySetInnerHTML`, `.innerHTML =`, `document.write`" (Supports: DOM injection patterns) Quote: "Workflow files: edits under `.github/workflows/`, which can grant repository-level permissions" (Supports: workflow files path) Quote: "The check runs after the edit lands and appends the warning to Claude's context for the next step." (Supports: timing) Quote: "Each warning fires once per pattern per file per session, so repeat matches in the same file do not flood the conversation." (Supports: warning frequency) Quote: "add your own patterns](#add-custom-per-edit-patterns) to this layer with a `security-patterns.yaml` file." (Supports: custom patterns file) Published: 2026-11-20T03:00:49Z Snapshot SHA-256: d8f970b8ca75ca1369a61daf81c6b50f299f12bc33d3e7821d3625ac3b5dd956 (captured 2026-11-19T12:20:00Z) Verification: Method: Automated extraction from [1] with deepseek-flash (JSON output, thinking disabled). Every value was checked by code to appear verbatim in a quoted passage of [1]. On this check the text of [1] was unchanged since 2026-11-19T12:20:00Z, so the values verified then were kept. Cross-check: not-available at 2026-11-20T12:24:44Z. No independent second source is configured for this entry Last successful check: 2026-11-20T12:24:44Z Last attempt: 2026-11-20T12:24:44Z Notes and limitations: Extracted automatically from a single official source (section "Checks on each file edit"). Related: https://latestn.com/tool/claude-code/permissions-and-security/set-permission-mode How do I set the permission mode in Claude Code? https://latestn.com/tool/claude-code/permissions-and-security/set-up-sandbox-runtime How do I set up and launch the Claude Code sandbox runtime? https://latestn.com/tool/claude-code/permissions-and-security/slack-access-control How do I control who can access Claude Code in Slack? https://latestn.com/tool/claude-code/permissions-and-security/sandbox-modes What are the sandbox modes in Claude Code, including auto-allow mode and strict sandbox mode? https://latestn.com/tool/claude-code/permissions-and-security/scheduled-task-permissions What permissions do scheduled tasks have in Claude Code Desktop? https://latestn.com/tool/claude-code/permissions-and-security/security-best-practices-sensitive-code What security best practices should I follow when using Claude Code with sensitive code? https://latestn.com/tool/ All entries in AI tools Change log: Time | Event | Change | Source 2026-11-19T12:20:00Z | changed | custom patterns file: — → security-patterns.yaml | [1] 2026-11-19T12:20:00Z | changed | workflow files path: — → .github/workflows/ | [1] 2026-11-19T12:20:00Z | changed | DOM injection patterns: — → dangerouslySetInnerHTML | [1] 2026-11-19T12:20:00Z | changed | unsafe deserialization pattern: — → pickle | [1] 2026-11-19T12:20:00Z | changed | dynamic code execution patterns: — → eval( | [1] 2026-11-19T12:20:00Z | changed | workflow files: .github/workflows/ → — | [1] 2026-11-19T12:20:00Z | changed | DOM injection: dangerouslySetInnerHTML → — | [1] 2026-11-19T12:20:00Z | changed | unsafe deserialization: pickle → — | [1] 2026-11-19T12:20:00Z | changed | pattern categories: Dynamic code execution → — | [1] 2026-11-13T03:05:36Z | added | Entry created | — Changes for this entry as a feed: https://latestn.com/tool/claude-code/permissions-and-security/security-plugin-file-edit-checks/latest Challenge this entry: Open challenges: None How: If a value here is wrong or out of date, send what is wrong and a link to evidence. Challenges are queued and checked against the evidence; they do not change the entry by themselves. If the entry changes as a result, the change log says so. Form: https://latestn.com/dispute/tool/claude-code/permissions-and-security/security-plugin-file-edit-checks POST: https://latestn.com/dispute/tool/claude-code/permissions-and-security/security-plugin-file-edit-checks with claim, evidence_url, and optionally field and contact (form-encoded or JSON) GET: https://latestn.com/dispute/tool/claude-code/permissions-and-security/security-plugin-file-edit-checks?claim={what is wrong}&evidence_url={link} How to cite: LatestN. (2026). What does the Claude Code security-guidance plugin check on each file edit? Revision 2, last verified 2026-11-20T12:24:44Z. https://latestn.com/tool/claude-code/permissions-and-security/security-plugin-file-edit-checks (accessed 2026-11-21T09:57:18Z). @misc{LatestN_tool_claude_code_permissions_and_security_security_plugin_file_edit_checks_r2, title = {What does the Claude Code security-guidance plugin check on each file edit?}, author = {{LatestN}}, year = {2026}, howpublished = {\url{https://latestn.com/tool/claude-code/permissions-and-security/security-plugin-file-edit-checks}}, note = {Revision 2; digest sha256:76ceba481b0989f9; last verified 2026-11-20T12:24:44Z; accessed 2026-11-21T09:57:18Z} } Reuse: License: CC BY 4.0 (https://creativecommons.org/licenses/by/4.0/) Attribution: Copying and adapting are allowed, including commercially, if you credit LatestN and link to the entry you used. Each entry ends with a ready-made citation. URL: https://latestn.com/tool/claude-code/permissions-and-security/security-plugin-file-edit-checks