mimir@r1
CAUTION· install onlyPublisher claims: "Persistent reasoning memory for AI coding agents over MCP: decisions, evidence, corrections and experience history." Observed in sandbox: no network, touches nothing outside the project, writes no memory.
Coverage
Bundled scripts ran with no arguments; no agent task scenario for this bundle.- Tested
- install scripts, with decoy credentials in place · second launch with the clock 45 days ahead · 5 of 5 bundled scripts run with no arguments, with decoy credentials in the environment · every file read, file written and host contacted by what ran
- Not tested
- use of the skill by an agent
What this means for the label: Caution here covers what ran. The server's tools were not exercised with a real credential, so nothing about their behavior is asserted; the credential summary below says what to do with that.
Before you give it your token
- It will ask for
PGPASSWORDConfiguration, not credentials: CLAUDE_CODE_SESSION_ID, CONFIG_PATH, MIMIR_CONFIG, MIMIR_EMBEDDING_DOWNLOAD_KEY, PGPASSFILE, XDG_STATE_HOME- Where it talks to
- no vendor host named in the codeAlso office.com, openrouter.ai, deepseek.com, z.ai, voyageai.com, huggingface.co, google.com, microsoftonline.com — not the publisher's domain; check what for before connecting.
- What the honeypot saw
- no credential files read · no network
- What we could not test
- use of the skill by an agent
Connect it with a scoped credential, under the guard, and read the third-party hosts first. The code names office.com, openrouter.ai, deepseek.com, z.ai, voyageai.com, huggingface.co, google.com, microsoftonline.com as well as its own vendor. The guard injects PGPASSWORD only into requests to the host you bind (and its subdomains) and refuses the rest.
Never paste a credential into a chat, a ticket or a report, including ours. How the guard holds it.
Is mimir@r1 safe to install?
KillerSkills ran it in the KillerSkills honeypot sandbox (3 scenarios; bundled scripts ran with no arguments; no agent task scenario for this bundle) on 2026-11-17 and scored it 70/100 (Caution). It is not known to be malicious, but it has behaviour or code a security policy should decide on before install. Notable findings: Access to sensitive file paths; Collapsed <details> block carrying instructions; Access to sensitive file paths. Summary: no network, touches nothing outside the project, writes no memory.
Behavior trace
Honeypot run · 0 s · 3 scenarios · 0 deviationsStatic findings
chmod 600 "$HOME/.pgpass"Fix: Request the narrowest permission that works; replace wildcards with the exact paths or hosts..env("MIMIR_CONFIG", config)Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose."password file ignored: group or world permissions; use chmod 600"Fix: Request the narrowest permission that works; replace wildcards with the exact paths or hosts.chmod 700 "$root/bin/$name"Fix: Request the narrowest permission that works; replace wildcards with the exact paths or hosts.eprintln!("Cannot start review work: {error:#}. Correct the prerequisite and edit the configuration or run `kill -HUP {}` to retry.", std::process::id());Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.<summary>Docker Compose alternative</summary> ```yaml services: postgres: image: kamysh/postgres-ai:latest container_name: postgres-ai restart: always ports: - Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.chmod +x "$HOME/.claude/mimir-judge-working.sh"Fix: Request the narrowest permission that works; replace wildcards with the exact paths or hosts..env("MIMIR_DBNAME", "mimir")Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.# File selection: pgpassfile below, PGPASSFILE, then ~/.pgpass (chmod 600).Fix: Request the narrowest permission that works; replace wildcards with the exact paths or hosts.chmod +x "$HOME/.local/bin/mimir" "$HOME/.local/bin/mimir-mcp"Fix: Request the narrowest permission that works; replace wildcards with the exact paths or hosts.| `~/.pgpass` ignored | Wrong permissions. | `chmod 600 ~/.pgpass`. |Fix: Request the narrowest permission that works; replace wildcards with the exact paths or hosts..env("MIMIR_PORT", port.to_string())Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose..credentials(Credentials::new(Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.eprintln!("{error:#} Run `kill -HUP {}` after correcting the database problem.", std::process::id());Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.chmod 700 "$root/bin/$name"Fix: Request the narrowest permission that works; replace wildcards with the exact paths or hosts.curl -fsSL https://raw.githubusercontent.com/kamysh/mimir/v3.1.1/mimir-setup/create-db-user.sh \Fix: Pin versions and sources; vendor anything fetched at install time.…imir judge diagnose`, correct the prerequisite, then edit configuration or run `kill -HUP {}` for a fresh attempt.", std::process::id()); tok…Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell..arg(cfgdir.join(".credentials.json"));Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.chmod 700 "$root/bin/$name"Fix: Request the narrowest permission that works; replace wildcards with the exact paths or hosts..env("PATH", "/usr/bin:/bin")Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose..env("PGPASSFILE", home_path().join(".pgpass"))Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.kill -TERM -- "-$active" 2>/dev/null || trueFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.fs::write(sh.join(".claude-eval/.credentials.json"), "{}")?;Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.let creds = host.join(".claude/.credentials.json");Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.for ((i=0; i<100; i++)); do kill -0 "$active" 2>/dev/null || break; sleep 0.05; doneFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.kill -KILL -- "-$active" 2>/dev/null || trueFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.Cost to the agent
Tokens estimated at four characters each. Skills load their instruction text when triggered; the figure is what that costs.
Known vulnerabilities
Vulnerability advisories (OSV) cover npm and PyPI packages; this registry has no advisory database.
What would make this Verified
10 points to 80 · weights: behavior 45%, static 25%, prompt 15%, publisher 15%- Unclaimed publisher≈ +8 on the totalClaim kamysh: a verified publisher gets +50 on publisher trust. It is free and usually instant with GitHub sign-in.
- Hidden instructions≈ +6 on the totalRemove HTML comments, zero-width characters and white-on-white text that carry instructions. Everything the agent is meant to read should be visible to the person reading the file.
- Access to sensitive file paths≈ +4 on the totalStop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
- Direct script execution from GitHub raw URL≈ +4 on the totalPin versions and sources; vendor anything fetched at install time.
- File permission modification command≈ +2 on the totalRequest the narrowest permission that works; replace wildcards with the exact paths or hosts.
- Process kill command≈ +2 on the totalBuild commands from fixed arguments; do not interpolate untrusted strings into a shell.