Skills/Glama/teamvault

teamvault@0.3.0

CAUTION· not started

Publisher claims: "Connects any number of AI agents — Claude Code, Codex, or any MCP client — to one git-backed Markdown vault of shared team memory, exposing tools for briefings, search, reading, recent changes, sharing facts, transcripts, and urgent-item acknowledgments. Agent writes are queued and reviewed by a librarian model, then privacy-checked, linted, and committed as attributed git changes, so every agent reads the same current truth." Observed in sandbox: no network, touches nothing outside the project, writes no memory.

Registry GlamaPublisher isaacbitran · publishing for 6 daysInstalls 0Last detonated 6d ago

Coverage

Not started: dependency install failed; the server itself was not observed.
Tested
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

It will ask for
TEAMVAULT_TOKENConfiguration, not credentials: CODEX_HOME, TEAMVAULT_CONFIG, TEAMVAULT_NO_CLAUDE_MD, VAULT_DIR
Where it talks to
no vendor host named in the codeAlso apple.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
server startup · the tool list · tool behavior

Connect it with a scoped credential, under the guard, and read the third-party hosts first. The code names apple.com as well as its own vendor. The guard injects TEAMVAULT_TOKEN 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 [email protected] safe to install?

KillerSkills ran it in the KillerSkills honeypot sandbox (2 scenarios; not started: dependency install failed; the server itself was not observed) on 2026-11-12 and scored it 72/100 (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; Hidden zero-width characters detected; Bidirectional text override characters detected. Summary: no network, touches nothing outside the project, writes no memory.

Behavior trace

Honeypot run · 0 s · 2 scenarios · 0 deviations
t+CategoryObserved action
0.0sprocessno install scripts in bundle
0.1sprocessdependency install exit 1 ·
0.1sclaimednot started: dependency install failed (exit 1); the server itself was not observed
0.1sprocessscript backend runs setup only
0.1sprocessno install scripts to re-run

Static findings

MEDIUM
File permission modification commandsrc/teamvault/static/setup-codex.sh:51 · File permission modification command — agent changes file ownership/permissionschmod +x "$CODEX/teamvault/refresh.sh" "$CODEX/teamvault/refresh.py"Fix: Request the narrowest permission that works; replace wildcards with the exact paths or hosts.
AST05
MEDIUM
Python subprocess execution detectedsrc/teamvault/vendor/vault_build.py:49 · Python subprocess execution detectedreturn subprocess.run(["git", "-C", str(VAULT), *args], capture_output=True, text=True, timeout=10).stdoutFix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
Python subprocess execution detectedsrc/teamvault/librarian.py:133 · Python subprocess execution detectedr = subprocess.run(args, cwd=config.VAULT, env=_child_env(), capture_output=True, text=True, timeout=600,Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
HIGH
Access to sensitive file pathssrc/teamvault/config.py:4 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system filesvariables win over the file. See `.env.example` for the full list.Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
HIGH
Hidden zero-width characters detectedsrc/teamvault/privacy.py:10 · Hidden zero-width characters detected — may conceal content_INVISIBLE = re.compile(r"[\U000E0000-\U000E007F​-‏‪-‮⁠-⁤]")Fix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.
AST07
LOW
Instructs the agent to modify its persistent memory or instruction filessrc/teamvault/vault.py:77 · 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 filegit("add", "CLAUDE.md"); git("commit", "-q", "-m", "update librarian rules", author="server")Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
MEDIUM
Python subprocess execution detectedsrc/teamvault/vendor/vault_lint.py:148 · Python subprocess execution detectedhead = subprocess.run(["git", "-C", str(VAULT), "show", f"HEAD:{rel}"], capture_output=True, text=True).stdoutFix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
Python subprocess execution detectedsrc/teamvault/librarian.py:116 · Python subprocess execution detectedreturn subprocess.run(config.BUSY_CMD, shell=True).returncode == 0Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
Python subprocess execution detectedtests/conftest.py:24 · Python subprocess execution detectedproc = subprocess.Popen([sys.executable, "-c", "import teamvault; teamvault.main()", "demo", str(root)],Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
Python subprocess execution detectedsrc/teamvault/vendor/vault_build.py:309 · Python subprocess execution detectedr = subprocess.run([RG, "-l", "-i", "-w", "--no-config", "--no-ignore", pat, *targets],Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
Python subprocess execution detectedsrc/teamvault/vault.py:33 · Python subprocess execution detectedr = subprocess.run(["git", "-C", str(VAULT), *args], capture_output=True, text=True, env=env, timeout=30,Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
Python subprocess execution detectedsrc/teamvault/vendor/vault_lint.py:147 · Python subprocess execution detecteddiff = subprocess.run(["git", "-C", str(VAULT), "diff", "-U0", "--", rel], capture_output=True, text=True).stdoutFix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
File permission modification commandsrc/teamvault/static/setup-codex.sh:42 · File permission modification command — agent changes file ownership/permissionsmkdir -p "$CODEX/teamvault"; printf '%s' "$TOKEN" > "$CODEX/teamvault/token"; chmod 600 "$CODEX/teamvault/token"Fix: Request the narrowest permission that works; replace wildcards with the exact paths or hosts.
AST05
HIGH
Bidirectional text override characters detectedsrc/teamvault/privacy.py:10 · Bidirectional text override characters detected — may hide content direction_INVISIBLE = re.compile(r"[\U000E0000-\U000E007F​-‏‪-‮⁠-⁤]")Fix: Replace encoded or assembled strings with plain literals and remove undeclared network calls.
AST07
MEDIUM
File permission modification commandsrc/teamvault/static/setup-claude.sh:51 · File permission modification command — agent changes file ownership/permissionschmod +x "$D/team-briefing.sh" "$D/team-urgent.sh"Fix: Request the narrowest permission that works; replace wildcards with the exact paths or hosts.
AST05
MEDIUM
File permission modification commandsrc/teamvault/static/setup-claude.sh:28 · File permission modification command — agent changes file ownership/permissionsD="$HOME/.config/teamvault"; mkdir -p "$D"; chmod 700 "$D"Fix: Request the narrowest permission that works; replace wildcards with the exact paths or hosts.
AST05
MEDIUM
File permission modification commandsrc/teamvault/static/setup-codex.sh:24 · File permission modification command — agent changes file ownership/permissionsCFG="$CODEX/config.toml"; touch "$CFG"; chmod 600 "$CFG"Fix: Request the narrowest permission that works; replace wildcards with the exact paths or hosts.
AST05
MEDIUM
Hidden zero-width characters detectedtests/test_privacy.py:42 · Hidden zero-width characters detected — may conceal contentassert privacy.clean("hel​lo\U000E0041") == "hello"Fix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.
AST07
MEDIUM
Python subprocess execution detectedsrc/teamvault/vault.py:133 · Python subprocess execution detectedr = subprocess.run([RG, "-i", "-n", "-F", "--no-config", "-g", "*.md", "-g", "!CONTEXT.md", "-g", "!INDEX.md",Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05

Cost to the agent

Instructions loaded
≈729 tok
2 files · 35 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

8 points to 80 · weights: behavior 45%, static 25%, prompt 15%, publisher 15%
  1. Unclaimed publisher≈ +8 on the totalClaim isaacbitran: a verified publisher gets +50 on publisher trust. It is free and usually instant with GitHub sign-in.
  2. 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.
  3. Hidden zero-width characters detected≈ +4 on the totalKeep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.
  4. Bidirectional text override characters detected≈ +4 on the totalReplace encoded or assembled strings with plain literals and remove undeclared network calls.
  5. New publisher≈ +3 on the totalTime clears this on its own after 14 and 30 days. Claiming the handle (+50) is the fastest way past it.
  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 isaacbitranPropose a patch to the maintainer