cli@0.90.0
VERIFIED· startup onlyPublisher claims: "Your AI agents know the code. They don't know the company. Local CLI and MCP server that checks your coding agent's change against your team's decisions from Jira, Confluence, Linear, Notion, Slack, Teams, Zoom, GitHub, GitLab, git history and repo docs." Observed in sandbox: no network, touches nothing outside the project, writes no memory.
Coverage
Startup only; authenticated tool behavior not tested.- Tested
- server startup over stdio (initialize sent) · every file read, file written and host contacted by what ran
- Not tested
- the tool list (the server exited before answering) · what the tools do when called with real credentials
What this means for the label: Verified 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
ALIGN_LLM_API_KEYALIGN_TOKENALIGN_TOKEN_STOREConfiguration, not credentials: ALIGN_DEBUG, ALIGN_ENV, ALIGN_GATEWAY_URL, ALIGN_INTERNAL, ALIGN_LLM_BASE_URL, ALIGN_LLM_PROVIDER, ALIGN_LLM_TIMEOUT_MS, ALIGN_NO_SYNC, ALIGN_OLLAMA_MODEL, ALIGN_RULES_ACK, ALIGN_TENANT_ID, ALIGN_WRAPPED, COLORFGBG, OLLAMA_CONTEXT_LENGTH, OLLAMA_HOST, PI_CODING_AGENT_DIR- Where it talks to
- no vendor host named in the codeAlso align.tech, git-scm.com, microsoft.com, atlassian.net, evil.com — not the publisher's domain; check what for before connecting.
- What we saw when it ran
- no credential files read · no network
- What we could not test
- the tool list (the server exited before answering) · what the tools do when called with real credentials
Connect it with a scoped credential, under the guard, and read the third-party hosts first. The code names align.tech, git-scm.com, microsoft.com, atlassian.net, evil.com as well as its own vendor. The guard injects ALIGN_LLM_API_KEY, ALIGN_TOKEN, ALIGN_TOKEN_STORE 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.
What changed since 0.86.0
vet-skills diff cli 0.86.0 0.90.0In the sandbox, this version reached for nothing 0.86.0 did not. Compared from the two recorded runs, not from source.
- No longer contacted
- atlassian.com, linear.app, notion.com, slack.com
The guard can hold an update like this until someone approves it (runtime.on_change: hold). A change that only shows with a real credential, or on a path the run did not reach, is not in a trace and so not in this comparison.
Is [email protected] safe to install?
KillerSkills ran it in the KillerSkills honeypot sandbox (2 scenarios; startup only; authenticated tool behavior not tested) on 2026-11-21 and scored it 85/100 (Verified). In what ran, nothing we could detect went wrong: no undeclared network egress, no credential reads, no persistent instruction writes. What it does with a real credential was not observed; the static findings and the publisher carry the rest of the score. Summary: no network, touches nothing outside the project, writes no memory.
Behavior trace
Honeypot run · 41 s · 2 scenarios · 0 deviationsStatic findings
* child's block pins all of them empty (a repo's .env must not choose whose data an agent's server imports), and Align's own backgroundFix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.* ignored. It matters beyond correctness: an agent that loads a repo's `.env` (cn, Cline) handsFix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.// `||`, not `??`: OLLAMA_HOST='' (a stock .env template, an unset compose variable)Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.* The environment `align mcp` serves. Directories hand out `npx -y @aligndottech/cli mcp`, so onFix: Pin versions and sources; vendor anything fetched at install time.* The environment `align mcp` serves. Directories hand out `npx -y @aligndottech/cli mcp`, so onFix: Pin versions and sources; vendor anything fetched at install time.* ignored. It matters beyond correctness: an agent that loads a repo's `.env` (cn, Cline) handsFix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.// fetch, the confirmation re-post, a later batch): a 502 or a kill after this point cannot orphan aFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.Cost to the agent
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
No advisories in OSV for @aligndottech/cli@0.90.0 as of 37 min ago. This is the package itself, not its dependencies.