Skills/Glama/brain

brain@0.4.0

CAUTION· not started

Publisher claims: "Enables AI agents to search a single local SQLite full-text index of past Claude Code and Codex sessions, Obsidian notes and attachments, GitHub activity, and imported Claude/ChatGPT chats, plus project timelines and recent items. It also lets one agent hand off a session briefing to another so work can continue in a different tool without re-explaining context." Observed in sandbox: no network, touches nothing outside the project, writes no memory.

Registry GlamaPublisher dakirchik · publishing for 7 daysInstalls 0Last detonated 7d ago
What would fix thisWatchDispute verdict

Coverage

Not started: dependency install failed; the server itself was not observed.
Tested
install scripts, with decoy credentials in place · second launch with the clock 45 days ahead · the dependency install step · every file read, file written and host contacted by what ran
Not tested
server startup · the tool list · tool behavior

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

Code inventory arrives with this version's next honeypot run.
It will ask for
unknown until the next run
Where it talks to
unknown until the next run
What the honeypot saw
no credential files read · no network
What we could not test
server startup · the tool list · tool behavior

Not enough was observed to say yet. Not started: dependency install failed; the server itself was not observed. This version's code has not been inventoried for credentials and hosts either; both arrive with its next honeypot run (popular servers first). `vet-skills try brain` runs it now and prints the full answer.

Never paste a credential into a chat, a ticket or a report, including ours. How the guard holds it.

Is [email protected] safe to install?

KillerSkills ran it in the KillerSkills honeypot sandbox (3 scenarios; not started: dependency install failed; the server itself was not observed) on 2026-11-07 and scored it 68/100 (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; Privileged sudo command; Privileged sudo command. Summary: no network, touches nothing outside the project, writes no memory.

Behavior trace

Honeypot run · 1 s · 3 scenarios
t+CategoryObserved action
0.3sfilesystemread ~/.local/share/agent-recall/venv/pyvenv.cfg · ~/.local/share/agent-recall/venv/bin/python3.11._pth · ~/.local/share/agent-recall/venv/lib/python3.11/site-packages · ~/.local/share/agent-recall/venv outside project
0.3sfilesystemwrote ~/.local/share/agent-recall/venv/pyvenv.cfg
0.3sprocessexec /usr/bin/dirname
0.3sprocessexec /usr/bin/cut
0.3sprocessexec /usr/bin/tr
0.3sprocessexec /usr/bin/uname
0.3sprocessexec /usr/bin/sed
0.3sprocessexec /usr/bin/python3.11
0.3sprocessexec /usr/bin/mkdir
0.3sprocessexec /tmp/ks-detonate-1A0bDL/setup/home/.local/share/agent-recall/venv/bin/python3.11
0.3sprocessexec /usr/bin/rm
0.3sprocessexited 1: [x] Still cannot create the environment. Install the venv package for your Python and run again.
0.5sprocessdependency install exit 1
0.5sprocessexec /usr/bin/date
0.5sprocessexec /usr/bin/timeout
0.5sprocessexec .venv/bin/brain
0.5sclaimedno tools/list reply (exit 0)
0.5sprocessscript backend runs setup only
0.6sprocesssecond launch, clock +45 days, CI unset
1.0sfilesystemread ~/.local/share/agent-recall/venv/pyvenv.cfg · ~/.local/share/agent-recall/venv/bin/python3.11._pth · ~/.local/share/agent-recall/venv/lib/python3.11/site-packages · ~/.local/share/agent-recall/venv outside project
1.0sfilesystemwrote ~/.local/share/agent-recall/venv/pyvenv.cfg
1.0sprocessexec /usr/bin/faketime
1.0sprocessexec /usr/bin/dirname
1.0sprocessexec /usr/bin/cut
1.0sprocessexec /usr/bin/tr
1.0sprocessexec /usr/bin/uname
1.0sprocessexec /usr/bin/sed
1.0sprocessexec /usr/bin/python3.11
1.0sprocessexec /usr/bin/mkdir
1.0sprocessexec /tmp/ks-detonate-1A0bDL/later/home/.local/share/agent-recall/venv/bin/python3.11
1.0sprocessexec /usr/bin/rm
1.0sprocessexited 1: [x] Still cannot create the environment. Install the venv package for your Python and run again.

Static findings

HIGH
Access to sensitive file pathsagent_recall/redact.py:3 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system filesAgent logs and notes routinely contain tokens pasted into a terminal or .env filesFix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
HIGH
Privileged sudo commandbrainctl.sh:140 · Privileged sudo command — agent may execute with elevated privilegeselif command -v zypper >/dev/null 2>&1; then echo "sudo zypper install -y python3"Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
Python subprocess execution detectedagent_recall/codex_bridge.py:255 · Python subprocess execution detectedself.process = subprocess.Popen(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
HIGH
Privileged sudo commandbrainctl.sh:138 · Privileged sudo command — agent may execute with elevated privilegeselif command -v dnf >/dev/null 2>&1; then echo "sudo dnf install -y python3"Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
HIGH
Privileged sudo commandbrainctl.sh:139 · Privileged sudo command — agent may execute with elevated privilegeselif command -v pacman >/dev/null 2>&1; then echo "sudo pacman -S --needed python"Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
File permission modification commandbrainctl.sh:218 · File permission modification command — agent changes file ownership/permissionschmod +x "$BIN_DIR/brain" "$BIN_DIR/brainctl"Fix: Request the narrowest permission that works; replace wildcards with the exact paths or hosts.
AST05
HIGH
Privileged sudo commandbrainctl.sh:137 · Privileged sudo command — agent may execute with elevated privilegesif [ "$what" = venv ]; then echo "sudo apt-get install -y python${ver}-venv"; else echo "sudo apt-get install -y python3 python3-venv"; fiFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
File type combined with upload actionagent_recall/cli.py:430 · File type combined with upload action — agent may exfiltrate local data filesremember_import(cfg, Path(args.output) / "manifest.json", archive_root=Path(args.output).resolve().parent)Fix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.
AST07
MEDIUM
Python subprocess execution detectedagent_recall/integrations.py:35 · Python subprocess execution detectedreturn subprocess.run(args, capture_output=True, text=True, timeout=60,Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
Python subprocess execution detectedagent_recall/handoff.py:373 · Python subprocess execution detectedreturn subprocess.run(cmd, input=text.encode("utf-8")).returncode == 0Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
Python subprocess execution detectedagent_recall/collectors/github.py:27 · Python subprocess execution detectedr = subprocess.run([gh, "auth", "token"], capture_output=True, text=True, timeout=15)Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
Python subprocess execution detectedagent_recall/scheduler.py:38 · Python subprocess execution detectedp = subprocess.run(args, input=input, capture_output=True, text=True, encoding="utf-8",Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
URL with embedded credentialstests/test_search_handoff.py:61 · URL with embedded credentials — may be phishing or credential leaking"key sk-ant-api03-abcdefghijklmnopqrstuvwx https://user:pa55w0rd@host/x")Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST07
MEDIUM
Python subprocess execution detectedtests/test_scheduler.py:343 · Python subprocess execution detectedproc = subprocess.run(["powershell.exe", "-NoProfile", "-ExecutionPolicy", "Bypass", "-File", str(script),Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
LOW
Instructs the agent to modify its persistent memory or instruction filesREADME.md:277 · Instructs the agent to modify its persistent memory or instruction files · informational: not an instruction file · informational: not an instruction file · informational: not an instruction fileTip: add to `CLAUDE.md` / `AGENTS.md`: *"Before asking me about past decisions, search the brain MCP."*Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
MEDIUM
Python subprocess execution detectedtests/test_scheduler.py:310 · Python subprocess execution detectedproc = subprocess.run([bash, script.as_posix(), "install", "--no-sync", "--no-mcp", *flags],Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
GitHub token pattern detectedtests/test_search_handoff.py:60 · GitHub token pattern detected — possible hardcoded or harvested tokentext = redact("token ghp_abcdefghijklmnopqrstuvwxyz0123456789AB and password=SuperSecret123 "Fix: Never read or enumerate credential locations; accept a documented environment variable instead.
AST03

Cost to the agent

Instructions loaded
≈34 tok
1 file · 57 in bundle
Tool list per prompt
≈0 tok
0 tools · 0 per tool
Handshake
no reply
launch to tools/list, stdio
Undocumented tools
0
description under 20 chars · avg 0

Tokens estimated at four characters each. The tool list is re-read by the agent on every turn, so it is the number to compare between servers that do the same job: ranked across the index.

Known vulnerabilities

Vulnerability advisories (OSV) cover npm and PyPI packages; this registry has no advisory database.

What would make this Verified

12 points to 80 · weights: behavior 45%, static 25%, prompt 15%, publisher 15%
  1. Unclaimed publisher≈ +8 on the totalClaim dakirchik: a verified publisher gets +50 on publisher trust. It is free and usually instant with GitHub sign-in.
  2. Touches files outside the project≈ +7 on the totalKeep reads and writes inside the working directory, or declare the exact paths in `filesystem:` and explain why in the README.
  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. Privileged sudo command≈ +4 on the totalBuild commands from fixed arguments; do not interpolate untrusted strings into a shell.
  5. Python subprocess execution detected≈ +2 on the totalBuild commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
  6. File permission modification command≈ +2 on the totalRequest the narrowest permission that works; replace wildcards with the exact paths or hosts.
Publish a new version to Glama, then queue it here. Not your skill? Claim the handle to get verdict changes by email.Claim dakirchikPropose a patch to the maintainer