mimir@r1

CAUTION· install only

Publisher 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.

Registry GlamaPublisher kamysh · publishing for 0 daysInstalls 0Last detonated 1 h ago

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.

$vet-skills run --net declared -- <the server's command>

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 deviations
t+CategoryObserved action
0.0sprocessinstall script run in the sandbox
0.0sprocessexited 1: Nix is required for this source-build helper; use release downloads otherwise.
0.0sprocessbundled script run in the sandbox with no arguments · not named in the instructions
0.1sprocessexited 1: ./scripts/check-release-source.sh: line 6: GITHUB_EVENT_NAME: missing workflow event
0.1sprocessbundled script run in the sandbox with no arguments
0.1sprocessexec /usr/bin/dirname
0.1sprocessexec /usr/bin/mktemp
0.1sprocessexec /usr/bin/openssl
0.1sprocessexec /usr/bin/mkdir
0.1sprocessexec /usr/bin/chmod
0.1sprocessexited 127: ./scripts/test-isolated.sh: line 91: jq: command not found
0.1sprocessbundled script run in the sandbox with no arguments · not named in the instructions
0.2sprocessexec /usr/bin/dirname
0.2sprocessexec /usr/bin/diff
0.2sprocessexec /usr/bin/sort
0.2sprocessexec /usr/bin/awk
0.2sprocessexited 2: awk: cannot open /tmp/ks-detonate-IK2PLG/scripts/home/work/acme-api/.claude/skills/mimir/spec/Mimir/ApplicationProtocol.agda (No such file or directory)
0.2sprocessbundled script run in the sandbox with no arguments · not named in the instructions
0.2sprocessbundled script run in the sandbox with no arguments · not named in the instructions
0.2sprocessexited 1: ./crates/cli/src/judge/retry_fixture.sh: line 4: $1: unbound variable
0.2sprocess5 of 5 bundled scripts run with no arguments
0.2sprocessscript backend runs setup only
0.2sprocessscript backend runs setup only
0.2sprocesssecond launch, clock +45 days, CI unset
0.3sprocessexited 1: Nix is required for this source-build helper; use release downloads otherwise.

Static findings

MEDIUM
File permission modification commandAGENTS.md:189 · File permission modification command — agent changes file ownership/permissionschmod 600 "$HOME/.pgpass"Fix: Request the narrowest permission that works; replace wildcards with the exact paths or hosts.
AST05
HIGH
Access to sensitive file pathscrates/cli/src/judge/mcp.rs:71 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system files.env("MIMIR_CONFIG", config)Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
MEDIUM
File permission modification commandcrates/core/src/password.rs:35 · File permission modification command — agent changes file ownership/permissions"password file ignored: group or world permissions; use chmod 600"Fix: Request the narrowest permission that works; replace wildcards with the exact paths or hosts.
AST05
MEDIUM
File permission modification commandscripts/test-isolated.sh:38 · File permission modification command — agent changes file ownership/permissionschmod 700 "$root/bin/$name"Fix: Request the narrowest permission that works; replace wildcards with the exact paths or hosts.
AST05
MEDIUM
Process kill commandcrates/cli/src/judge/watcher.rs:65 · Process kill command — agent can terminate processeseprintln!("Cannot start review work: {error:#}. Correct the prerequisite and edit the configuration or run `kill -HUP {}` to retry.", std::process::id());Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
HIGH
Collapsed <details> block carrying instructionsREADME.md:153 · Collapsed <details> block carrying instructions<summary>Docker Compose alternative</summary> ```yaml services: postgres: image: kamysh/postgres-ai:latest container_name: postgres-ai restart: always ports: - Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
MEDIUM
File permission modification commandAGENTS.md:355 · File permission modification command — agent changes file ownership/permissionschmod +x "$HOME/.claude/mimir-judge-working.sh"Fix: Request the narrowest permission that works; replace wildcards with the exact paths or hosts.
AST05
HIGH
Access to sensitive file pathstools/qa/src/main.rs:41 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system files.env("MIMIR_DBNAME", "mimir")Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
MEDIUM
File permission modification commandcrates/core/src/config.rs:378 · File permission modification command — agent changes file ownership/permissions# File selection: pgpassfile below, PGPASSFILE, then ~/.pgpass (chmod 600).Fix: Request the narrowest permission that works; replace wildcards with the exact paths or hosts.
AST05
MEDIUM
File permission modification commandAGENTS.md:219 · File permission modification command — agent changes file ownership/permissionschmod +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.
AST05
MEDIUM
File permission modification commandAGENTS.md:423 · File permission modification command — agent changes file ownership/permissions| `~/.pgpass` ignored | Wrong permissions. | `chmod 600 ~/.pgpass`. |Fix: Request the narrowest permission that works; replace wildcards with the exact paths or hosts.
AST05
HIGH
Access to sensitive file pathstools/qa/src/main.rs:40 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system files.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.
AST05
HIGH
Access to sensitive file pathscrates/notifications/src/smtp.rs:121 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system files.credentials(Credentials::new(Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
MEDIUM
Process kill commandcrates/cli/src/judge/watcher.rs:94 · Process kill command — agent can terminate processeseprintln!("{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.
AST05
MEDIUM
File permission modification commandscripts/test-isolated.sh:42 · File permission modification command — agent changes file ownership/permissionschmod 700 "$root/bin/$name"Fix: Request the narrowest permission that works; replace wildcards with the exact paths or hosts.
AST05
HIGH
Direct script execution from GitHub raw URLAGENTS.md:197 · Direct script execution from GitHub raw URL — unverified code sourcecurl -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.
AST06
MEDIUM
Process kill commandcrates/cli/src/judge/watcher.rs:122 · Process kill command — agent can terminate processes…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.
AST05
MEDIUM
Access to sensitive file pathstests/eval/main.rs:1790 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system files.arg(cfgdir.join(".credentials.json"));Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
MEDIUM
File permission modification commandscripts/test-isolated.sh:46 · File permission modification command — agent changes file ownership/permissionschmod 700 "$root/bin/$name"Fix: Request the narrowest permission that works; replace wildcards with the exact paths or hosts.
AST05
MEDIUM
Access to sensitive file pathstests/eval/main.rs:1818 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system files.env("PATH", "/usr/bin:/bin")Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
MEDIUM
Access to sensitive file pathstests/eval/main.rs:978 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system files.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.
AST05
MEDIUM
Process kill commandscripts/test-isolated.sh:72 · Process kill command — agent can terminate processeskill -TERM -- "-$active" 2>/dev/null || trueFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
Access to sensitive file pathstests/eval/main.rs:1727 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system filesfs::write(sh.join(".claude-eval/.credentials.json"), "{}")?;Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
MEDIUM
Access to sensitive file pathstests/eval/main.rs:1786 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system fileslet creds = host.join(".claude/.credentials.json");Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
MEDIUM
Process kill commandscripts/test-isolated.sh:73 · Process kill command — agent can terminate processesfor ((i=0; i<100; i++)); do kill -0 "$active" 2>/dev/null || break; sleep 0.05; doneFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
Process kill commandscripts/test-isolated.sh:74 · Process kill command — agent can terminate processeskill -KILL -- "-$active" 2>/dev/null || trueFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05

Cost to the agent

Instructions loaded
≈9,632 tok
3 files · 80 in bundle

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%
  1. 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.
  2. 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.
  3. 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.
  4. Direct script execution from GitHub raw URL≈ +4 on the totalPin versions and sources; vendor anything fetched at install time.
  5. File permission modification command≈ +2 on the totalRequest the narrowest permission that works; replace wildcards with the exact paths or hosts.
  6. Process kill command≈ +2 on the totalBuild commands from fixed arguments; do not interpolate untrusted strings into a shell.
Publish a new version to Glama, then queue it here. Not your skill? Claim the handle to get verdict changes by email.Claim kamyshPropose a patch to the maintainer