Answer: Gemini CLI activates an Agent Skill by calling the `activate_skill` tool when it identifies a task matching a skill's description, and consent is requested via a confirmation prompt in the UI detailing the skill's name, purpose, and the directory path it will gain access to. Status: Confirmed Entry: tool/gemini-cli/permissions-and-security/skill-activation-consent Revision: 1 Digest: sha256:efe69891bdeb93e8 (changes whenever the content changes) Timeline: Created: 2026-11-13T03:17:47Z Last changed: 2026-11-13T03:17:47Z Last verified: 2026-11-20T12:51:31Z Next check: 2026-11-21T12:51:31Z Check interval: Daily Expected change: No fixed schedule Data: Field | Value | Source | As of activation tool | activate_skill | [1] | 2026-11-20 consent prompt | confirmation prompt in the UI | [1] | 2026-11-20 prompt details | skill's name, purpose, and the directory path | [1] | 2026-11-20 Sources: [1] Google. "Agent Skills". https://geminicli.com/docs/cli/skills.md Role: primary. Accessed: 2026-11-20T12:51:31Z Quote: "it calls the `activate_skill` tool" (Supports: activation tool) Quote: "You will see a confirmation prompt in the UI detailing the" (Supports: consent prompt) Quote: "skill's name, purpose, and the directory path it will gain access to" (Supports: prompt details) Published: 2026-10-16T02:36:07Z Snapshot SHA-256: 8e1b4cbe2cd31effa3375aa5d480269ab28bf82c02a42d9b52cbb61e5b248590 (captured 2026-11-13T03:17:47Z) 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 2026-11-13T03:17:47Z, so the values verified then were kept. Cross-check: not-available at 2026-11-20T12:51:31Z. No independent second source is configured for this entry Last successful check: 2026-11-20T12:51:31Z Last attempt: 2026-11-20T12:51:31Z Notes and limitations: Extracted automatically from a single official source (section "How it works"). Related: https://latestn.com/tool/gemini-cli/permissions-and-security/skill-security-privacy What security and privacy considerations should I follow when creating Gemini CLI Agent Skills? 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/sandboxing-methods Which sandboxing methods does Gemini CLI support on macOS, Linux, and Windows? 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/ All entries in AI tools Change log: Time | Event | Change | Source 2026-11-13T03:17:47Z | added | Entry created | — Changes for this entry as a feed: https://latestn.com/tool/gemini-cli/permissions-and-security/skill-activation-consent/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-activation-consent POST: https://latestn.com/dispute/tool/gemini-cli/permissions-and-security/skill-activation-consent 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-activation-consent?claim={what is wrong}&evidence_url={link} How to cite: LatestN. (2026). How does Gemini CLI activate an Agent Skill and ask for consent? Revision 1, last verified 2026-11-20T12:51:31Z. https://latestn.com/tool/gemini-cli/permissions-and-security/skill-activation-consent (accessed 2026-11-21T10:02:07Z). @misc{LatestN_tool_gemini_cli_permissions_and_security_skill_activation_consent_r1, title = {How does Gemini CLI activate an Agent Skill and ask for consent?}, author = {{LatestN}}, year = {2026}, howpublished = {\url{https://latestn.com/tool/gemini-cli/permissions-and-security/skill-activation-consent}}, note = {Revision 1; digest sha256:efe69891bdeb93e8; last verified 2026-11-20T12:51:31Z; accessed 2026-11-21T10:02:07Z} } 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-activation-consent