Skills/Glama/trace-canvas

trace-canvas@0.3.5

CAUTION· install only

Publisher claims: "Enables AI agents to capture coding sessions onto a shared transit map of threads and records, then list, read, fork, merge and log entries on it. It also exposes running sessions and per-thread goals and to-dos, so a new session can catch up on prior work across projects instead of rereading old chats." Observed in sandbox: no network, touches nothing outside the project, writes no memory.

Registry GlamaPublisher callsymmetryecho · publishing for 1 daysInstalls 0Last detonated 20 h ago
What would fix thisWatchDispute verdict

Coverage

Nothing executable in the bundle ran; the trace covers the install step only.
Tested
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
no credential variables read in the code
Where it talks to
no vendor host named in the codeAlso tldraw.dev, jsoncanvas.org, claude.ai — 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 under the guard. Nothing executable in the bundle ran; the trace covers the install step only. The code names no credential variable; the guard pins the network to what the honeypot saw and logs every call.

$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 (1 scenario; nothing executable in the bundle ran; the trace covers the install step only) on 2026-11-13 and scored it 79/100 (Caution). It is not known to be malicious, but it has behaviour or code a security policy should decide on before install. Notable findings: Privileged sudo command; Access to sensitive file paths. Summary: no network, touches nothing outside the project, writes no memory.

Behavior trace

Honeypot run · 0 s · 1 scenarios · 0 deviations
t+CategoryObserved action
0.0sprocessno install scripts in bundle
0.0sprocessscript backend runs setup only
0.0sprocessscript backend runs setup only
0.0sprocessno install scripts to re-run

Static findings

MEDIUM
Access to sensitive file pathstest/git-view.test.mjs:45 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system filesassert.match((await commitDiff(d, 'r1', '../../etc/passwd')).error, /not part of this change/);Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
MEDIUM
File type combined with upload actionbin/trace-canvas.mjs:282 · File type combined with upload action — agent may exfiltrate local data filesconsole.log(`Forked "${r.thread.name}"${sid ? ` and put session ${sid} on it` : ''}`);Fix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.
AST07
MEDIUM
Access to sensitive file pathstest/install.test.mjs:158 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system filesassert.deepEqual(terminalCommand('ls', { ...env, TERMINAL: 'gnome-terminal' }, 'linux')[1].slice(0, 3), ['--tab', '--', '/bin/bash']);Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
MEDIUM
File type combined with upload actionbin/trace-canvas.mjs:511 · File type combined with upload action — agent may exfiltrate local data filesconsole.log(` total ${k(all.fresh)} · ${k(all.cached)} · ${k(all.output)} = ${k(tot(all))}`);Fix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.
AST07
MEDIUM
Access to sensitive file pathstest/install.test.mjs:164 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system files…nherit who the caller is (it would be the caller's child). const caller = { ...env, CLAUDECODE: '1', CLAUDE_PID: '9', CLAUDE_CODE_SESSION_ID: 'caller', CLAUDE_COD…Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
HIGH
Privileged sudo commandbin/trace-canvas.mjs:562 · Privileged sudo command — agent may execute with elevated privileges} catch { console.log(`The page server runs as systemd ${unit.name}; restart it with: ${unit.user ? 'systemctl --user' : 'sudo systemctl'} restart ${unit.name}`); }Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
File type combined with upload actionbin/trace-canvas.mjs:509 · File type combined with upload action — agent may exfiltrate local data files…resh: 0, cached: 0, output: 0 }); add(main); add(w); console.log(` ${s.id.slice(0, 8)} itself ${k(main.fresh)} · ${k(main.cached)} · ${k(main.output)} = ${k(tot(main))}${subagents.length ? `; ${subagents.length} subagent${subagents.length …Fix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.
AST07
MEDIUM
Access to sensitive file pathstest/install.test.mjs:168 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system filesconst gt = { ...env, TERMINAL: 'gnome-terminal', GNOME_TERMINAL_SCREEN: '/org/gnome/Terminal/screen/mine' };Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
MEDIUM
File type combined with upload actionbin/trace-canvas.mjs:152 · File type combined with upload action — agent may exfiltrate local data files…opilot's rules reach the caller too else if (r.action === 'message') console.log(` → Running session ${name} (${s.status}${s.name ? `, messaged as ${s.name}` : ''}${s.desktopId ? `, ${s.desktopId}` : ''}): send it this message:\n ${r.promp…Fix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.
AST07
MEDIUM
File type combined with upload actionsrc/mcp.mjs:108 · File type combined with upload action — agent may exfiltrate local data files…ption: 'Merges another Trace Canvas data set into this one: an export file, data.json copied from another computer, or JSON lines from an agent. Threads with the same repository/branch or sess…Fix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.
AST07
MEDIUM
File type combined with upload actionbin/trace-canvas.mjs:501 · File type combined with upload action — agent may exfiltrate local data filesconsole.log(`Since ${since ? new Date(since).toISOString() : 'the start'} on "${th.name}" (fresh input · cache reads · output):`);Fix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.
AST07
HIGH
Access to sensitive file pathssrc/agents.mjs:53 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system filesif (vars.DISPLAY || vars.WAYLAND_DISPLAY) return { ...env, ...Object.fromEntries(KEEP.filter(k => vars[k]).map(k => [k, vars[k]])) };Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
MEDIUM
npx invocation of non-well-known packagetest/live.test.mjs:160 · npx invocation of non-well-known package — may execute untrusted code…ession_id: cli, hook_event_name: ev, tool_name: 'Bash', tool_input: { command: 'npx remotion render' } }, { env: s.env }); const { sessions, others } = liveSessions(readD…Fix: Pin versions and sources; vendor anything fetched at install time.
AST06
LOW
Instructs the agent to modify its persistent memory or instruction filesREADME.md:339 · Instructs the agent to modify its persistent memory or instruction files · informational: not an instruction file…finally made it clear and suggests a rule. Nothing is written until you press **Write** on a rule and pick where it goes: **project rules** (the project's CLAUDE.md and AGENTS.md, under "Rules from retros"), **this line** (a decision on th…Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
LOW
Instructs the agent to modify its persistent memory or instruction filesCHANGELOG.md:116 · Instructs the agent to modify its persistent memory or instruction files · informational: not an instruction file…e sentence that made it clear and a rule; a rule is written only when you press Write, to the project's CLAUDE.md and AGENTS.md, the line, or long-term memory. - **Fewer tokens:** `trace_tasks` answers for t…Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
LOW
Instructs the agent to modify its persistent memory or instruction filesbin/trace-canvas.mjs:114 · Instructs the agent to modify its persistent memory or instruction files · informational: not an instruction fileWrite suggestion n: CLAUDE.md/AGENTS.md, the line, or long-term memoryFix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
LOW
Fake instruction boundary tagdocs/phone.md:40 · Fake instruction boundary tag · informational: not an instruction fileclaude --remote-control='<line name>' '<prompt>'Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
MEDIUM
Access to sensitive file pathstest/reply.test.mjs:21 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system fileshandleHook({ session_id: sid, cwd: root, hook_event_name: 'UserPromptSubmit', prompt: 'next' }, { ...env, CLAUDE_PID: '103' });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 pathstest/step0.test.mjs:45 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system filesassert.equal(currentSessionId({ projectDir: project, env: { ...env, CLAUDE_CODE_SESSION_ID: 'mine' } }), 'mine');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 pathstest/step0.test.mjs:46 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system filesassert.equal(currentSessionId({ sessionId: 'explicit', projectDir: project, env: { ...env, CLAUDE_CODE_SESSION_ID: 'mine' } }), 'explicit');Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05

Cost to the agent

Instructions loaded
≈3,133 tok
1 file · 78 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

1 point to 80 · weights: behavior 45%, static 25%, prompt 15%, publisher 15%
  1. Unclaimed publisher≈ +8 on the totalClaim callsymmetryecho: a verified publisher gets +50 on publisher trust. It is free and usually instant with GitHub sign-in.
  2. Privileged sudo command≈ +4 on the totalBuild commands from fixed arguments; do not interpolate untrusted strings into a shell.
  3. Access to sensitive file paths≈ +2 on the totalStop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
  4. File type combined with upload action≈ +2 on the totalRemove the call, or declare the host in frontmatter and explain in the README what is sent and why.
  5. npx invocation of non-well-known package≈ +2 on the totalPin versions and sources; vendor anything fetched at install time.
Publish a new version to Glama, then queue it here. Not your skill? Claim the handle to get verdict changes by email.Claim callsymmetryechoPropose a patch to the maintainer