Aider
Aider · CLI agent · homepage · Aider-AI/aider
No minimum safe version: none of Aider's medium-or-higher advisories states a fixed version we can compare. Only advisories for Aider itself are counted. 1 medium-or-higher advisory lists no fixed version: check the vendor's guidance before relying on the minimum.
Advisories · Data exposure · Hardening
Advisories
| ID | Title | Severity | Fixed in | Published |
|---|---|---|---|---|
| CVE-2026-85674 | aider (aider-chat) automatically loads a .aider.conf.yml configuration file from the root of the git repository it is launched in. A crafted… | High | — | 2026-09-04 |
| CVE-2026-10177 | Aider has an SSRF vulnerability through its AWS EC2 Metadata Endpoint | Low | — | 2026-05-31 |
| CVE-2026-10175 | Aider is vulnerable to Code Injection via editor_coder.run function | Low | — | 2026-05-31 |
Hardening checklist
- Keep auto-update enabled and verify the installed version against the minimum safe version.
- Do not open untrusted repositories with agent mode or auto-approve enabled.
- Restrict MCP servers to an allowlist; review each server's permissions and publisher.
- Never place secrets in project files the agent can read; use a secrets manager or env injection.
Data exposure
What Aider keeps on a developer machine, what it sends, and the settings that reduce exposure. Local transcripts can contain anything pasted into a session, including secrets: include these paths in secret scanning and offboarding.
Stored locally
| What | Where |
|---|---|
| Chat history in Markdown. | .aider.chat.history.md (default; set with --chat-history-file) |
| Chat input history. | .aider.input.history (default; set with --input-history-file) |
| Full conversation with the LLM, only when enabled. | File given to --llm-history-file (for example .aider.llm.history) |
API keys and settings, if stored in .env. | .env in your home directory, the git repo root or the current directory |
Sent to the vendor
Chat and the files you add go to the LLM provider you configure. Aider's analytics are opt-in, use a random anonymous ID, and never include code, chat messages, keys or personal info.
Retention and training
Retention and training follow the terms of the LLM provider you configure.
Settings that reduce exposure
--analytics-disable- Permanently disables analytics.
--gitignore(default on)- Adds
.aider*files to.gitignoreso history files are not committed. --chat-history-file/--input-history-file- Moves history files to a location you choose.
--aiderignore(default.aiderignorein git root)- Excludes listed files from Aider.
Sources: Aider docs: Options reference · Aider docs: Analytics · Aider docs: Config with .env · reviewed 2026-11-09
Rolling these tools out? See the playbook Secure AI coding tools in your organisation.
Lock it down: AI hardening kit (managed settings and MCP allowlist generators, free, in your browser).
Check your version
Via the public API:
curl -s "https://threatdeck.net/api/v1/tools/aider/check?version=<your-version>" Or ask your agent through the ThreatDeck MCP server (https://threatdeck.net/mcp):
check_ai_tool_version { "slug": "aider", "version": "<your-version>" } Updated 2026-11-22