Answer: When creating Gemini CLI Agent Skills, avoid hardcoded secrets, review third-party skills before installing them from an untrusted source, and limit scope to minimize the potential impact of errors. Status: Confirmed Entry: tool/gemini-cli/permissions-and-security/skill-security-privacy Revision: 1 Digest: sha256:6a06857dd431ce9e (changes whenever the content changes) Timeline: Created: 2026-11-13T03:17:46Z Last changed: 2026-11-13T03:17:46Z Last verified: 2026-11-20T12:51:28Z Next check: 2026-11-21T12:51:28Z Check interval: Daily Expected change: No fixed schedule Data: Field | Value | Source | As of Secrets guidance | Avoid hardcoded secrets | [1] | 2026-11-20 Third-party skills guidance | Review third-party skills | [1] | 2026-11-20 Scope guidance | Limit scope | [1] | 2026-11-20 Sources: [1] Google. "Agent Skill best practices". https://geminicli.com/docs/cli/skills-best-practices.md Role: primary. Accessed: 2026-11-20T12:51:28Z Quote: "**Avoid hardcoded secrets**: Never include API keys or passwords in your" (Supports: Secrets guidance) Quote: "**Review third-party skills**: Inspect the `SKILL.md` and scripts of any skill" (Supports: Third-party skills guidance) Quote: "**Limit scope**: Design skills to be as focused as possible to minimize the" (Supports: Scope guidance) Published: 2026-10-16T02:36:07Z Snapshot SHA-256: 612c3b8396fdc6669702127975c5d4ec5ce59bd8355fdbfb837fdd83d3d524c3 (captured 2026-11-13T03:17:45Z) 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 2026-11-13T03:17:46Z, so the values verified then were kept. Cross-check: not-available at 2026-11-20T12:51:28Z. No independent second source is configured for this entry Last successful check: 2026-11-20T12:51:28Z Last attempt: 2026-11-20T12:51:28Z Notes and limitations: Extracted automatically from a single official source (section "Security and privacy"). Related: https://latestn.com/tool/gemini-cli/permissions-and-security/tool-execution-security How does Gemini CLI handle confirmation and sandboxing for tool execution? https://latestn.com/tool/gemini-cli/permissions-and-security/untrusted-workspace-impact What happens when I run Gemini CLI in an untrusted folder? https://latestn.com/tool/gemini-cli/permissions-and-security/web-fetch-confirmation Does the Gemini CLI web_fetch tool require confirmation, including in Plan Mode? https://latestn.com/tool/gemini-cli/permissions-and-security/secure-api-key-storage What is the best way to store my API keys securely for Gemini CLI? https://latestn.com/tool/gemini-cli/permissions-and-security/shell-command-safety-features What safety features like confirmation prompts and sandboxing does Gemini CLI have for shell commands? https://latestn.com/tool/gemini-cli/permissions-and-security/skill-activation-consent How does Gemini CLI activate an Agent Skill and ask for consent? https://latestn.com/tool/ All entries in AI tools Change log: Time | Event | Change | Source 2026-11-13T03:17:46Z | added | Entry created | — Changes for this entry as a feed: https://latestn.com/tool/gemini-cli/permissions-and-security/skill-security-privacy/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/gemini-cli/permissions-and-security/skill-security-privacy POST: https://latestn.com/dispute/tool/gemini-cli/permissions-and-security/skill-security-privacy with claim, evidence_url, and optionally field and contact (form-encoded or JSON) GET: https://latestn.com/dispute/tool/gemini-cli/permissions-and-security/skill-security-privacy?claim={what is wrong}&evidence_url={link} How to cite: LatestN. (2026). What security and privacy considerations should I follow when creating Gemini CLI Agent Skills? Revision 1, last verified 2026-11-20T12:51:28Z. https://latestn.com/tool/gemini-cli/permissions-and-security/skill-security-privacy (accessed 2026-11-21T09:58:50Z). @misc{LatestN_tool_gemini_cli_permissions_and_security_skill_security_privacy_r1, title = {What security and privacy considerations should I follow when creating Gemini CLI Agent Skills?}, author = {{LatestN}}, year = {2026}, howpublished = {\url{https://latestn.com/tool/gemini-cli/permissions-and-security/skill-security-privacy}}, note = {Revision 1; digest sha256:6a06857dd431ce9e; last verified 2026-11-20T12:51:28Z; accessed 2026-11-21T09:58:50Z} } 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/gemini-cli/permissions-and-security/skill-security-privacy