Skills/npm/frely-cli

frely-cli@0.23.34

CAUTION· not started

Publisher claims: "Frely CLI — FrelyMCP gives ChatGPT, Claude, Codex and other MCP clients access to your computer" Observed in sandbox: no network, touches nothing outside the project, writes no memory.

Registry npm (MCP server)Publisher frelyhq · publishing for 65 daysInstalls 9,563Last detonated 8d ago
What would fix thisWatchDispute verdict

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

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 frely-cli` 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 (2 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: Reads credential paths from the home directory; Privileged sudo command; Access to sensitive file paths. Summary: no network, touches nothing outside the project, writes no memory.

Behavior trace

Honeypot run · 1 s · 2 scenarios · 0 deviations
t+CategoryObserved action
0.0sprocessno install scripts in bundle
0.8sprocessdependency install exit 1
1.0sprocessexec /usr/bin/date
1.0sprocessexec /usr/bin/timeout
1.0sclaimedno tools/list reply (exit 0)
1.0sprocessscript backend runs setup only
1.0sprocessno install scripts to re-run

Static findings

CRITICAL
Reads credential paths from the home directorydist/runtime/mcp.js:106 · Reads credential paths from the home directorytool("process", "Run shell commands as the current OS user, inside the OS sandbox, and refused when this device cannot sandbox them unless the owner turned the sandbox off: credential folders blocked Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST03
HIGH
Privileged sudo commanddist/service.js:200 · Privileged sudo command — agent may execute with elevated privilegesreturn `Warning: lingering is off for ${user}, so this device goes offline when your SSH session ends. Run \`sudo loginctl enable-linger ${user}\` to keep it online.`;Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
HIGH
Access to sensitive file pathsdist/agent-help.d.ts:673 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system filesreadonly purpose: "Send the complete relevant user request to the installed Agent through model-scoped MCP. Usage may be billed. The call runs in a background worker and is recorded on this computer (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 pathsdist/agent-help.d.ts:150 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system filesreadonly purpose: "Send the complete relevant user request to the installed Agent through model-scoped MCP. Usage may be billed. The call runs in a background worker and is recorded on this computer (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 pathsdist/skill/entry.js:26 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system files- Install a marketplace Skill or Prompt: \`frely item install <username/skill-name> --host <your host> --json\`; add \`--scope project --dir <project>\` to install it for one project instead of globalFix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
HIGH
Access to sensitive file pathsdist/agent-help.js:27 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system files{ id: "agent.run", usage: "frely agent run <username/name> (--input <text>|--input-stdin) [--read [<dir>] [--read-max-bytes <n>] [--read-max-rounds <n>]] [--progress-summary|--no-progress-summary] [--Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
HIGH
Outbound HTTP to raw IP addressdist/runtime/mcp.js:47 · Outbound HTTP to raw IP address — may bypass domain-based monitoringexport const LOCAL_MODELS_TOOL = tool("local_models", "Use a model server running on this device (Ollama, LM Studio, vLLM, llama.cpp, mltf) through Frely. action=list probes loopback OpenAI-compatibleFix: Replace encoded or assembled strings with plain literals and remove undeclared network calls.
AST07
HIGH
Access to sensitive file pathsdist/runtime/mcp.js:106 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system filestool("process", "Run shell commands as the current OS user, inside the OS sandbox, and refused when this device cannot sandbox them unless the owner turned the sandbox off: credential folders blocked 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 pathsdist/skill/entry.d.ts:5 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system filesexport declare const ENTRY_SKILL = "---\nname: frely\ndescription: Use when the user wants to work with their Frely account or the Frely marketplace through the frely CLI (credits, API keys, plans, orFix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
MEDIUM
Process kill commanddist/agent-help.js:78 · Process kill command — agent can terminate processes{ id: "api", usage: "frely api list|describe|call [--wait] [--help]", auth: "login", effect: "subcommand-dependent", purpose: "Discover and call your Frely account's business operations (the same toolFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
Process kill commanddist/agent-help.d.ts:456 · Process kill command — agent can terminate processesreadonly purpose: "Discover and call your Frely account's business operations (the same tools FrelyMCP offers through frely_list/frely_call). Read-only discovery runs on the account's own login; the fFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
File type combined with upload actiondist/provider/key.js:2 · File type combined with upload action — agent may exfiltrate local data files/** The upstream key of a local Provider (a NewAPI, vLLM or other gateway that wants one). Kept with the CLI's other secrets; never in local-providers.json, never uploaded. */Fix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.
AST07
MEDIUM
Process kill commanddist/auth.js:257 · Process kill command — agent can terminate processes/** Continues a browser login whose process ended before the owner approved (an agent shell can kill it): waits on the saved device code until it expires. */Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
File type combined with upload actiondist/link-claim.js:37 · File type combined with upload action — agent may exfiltrate local data filesoptions.log("Remote control was turned off from the web; locking this computer.");Fix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.
AST07
MEDIUM
Process kill commanddist/auth.d.ts:158 · Process kill command — agent can terminate processes/** Continues a browser login whose process ended before the owner approved (an agent shell can kill it): waits on the saved device code until it expires. */Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
Process kill commanddist/agent-help.js:258 · Process kill command — agent can terminate processeskill: "frely kill <device> <id>",Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
Process kill commanddist/agent-help.d.ts:928 · Process kill command — agent can terminate processesreadonly usage: "frely kill <device> <id>";Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
LOW
Instructs the agent to modify its persistent memory or instruction filesdist/skill/access.js:373 · 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 filereturn `---\nname: ${slug}\ndescription: ${JSON.stringify(description)}\ncompatibility: ${JSON.stringify("Requires frely-cli and network access to Frely.")}\nmetadata:\n frely-distribution-id: ${JSONFix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
MEDIUM
File permission modification commanddist/app-manager.js:282 · File permission modification command — agent changes file ownership/permissionsconst chmod = await d.run("chmod", ["+x", target]);Fix: Request the narrowest permission that works; replace wildcards with the exact paths or hosts.
AST05
LOW
Instructs the agent to modify its persistent memory or instruction filesdist/agent-help.d.ts:673 · 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 filereadonly purpose: "Send the complete relevant user request to the installed Agent through model-scoped MCP. Usage may be billed. The call runs in a background worker and is recorded on this computer (Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
MEDIUM
File permission modification commanddist/diagnostics.js:62 · File permission modification command — agent changes file ownership/permissions: `Configuration unreadable. Use owner-only permissions: chmod 700 ${dirname(mcpMetadataPath())} && chmod 600 ${mcpMetadataPath()}`Fix: Request the narrowest permission that works; replace wildcards with the exact paths or hosts.
AST05
MEDIUM
Process kill commanddist/agent-help.js:70 · Process kill command — agent can terminate processes{ id: "kill", usage: "frely kill <device> <id>", auth: "login", effect: "remote-execution", purpose: "Stop a background command on a device." },Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
Process kill commanddist/agent-help.d.ts:979 · Process kill command — agent can terminate processesreadonly purpose: "Discover and call your Frely account's business operations (the same tools FrelyMCP offers through frely_list/frely_call). Read-only discovery runs on the account's own login; the fFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
LOW
Instructs the agent to modify its persistent memory or instruction filesdist/agent-help.js:27 · 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 file{ id: "agent.run", usage: "frely agent run <username/name> (--input <text>|--input-stdin) [--read [<dir>] [--read-max-bytes <n>] [--read-max-rounds <n>]] [--progress-summary|--no-progress-summary] [--Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
MEDIUM
MCP server using network transport (SSE/HTTP)dist/skill/entry.d.ts:5 · MCP server using network transport (SSE/HTTP) — data sent over networkexport declare const ENTRY_SKILL = "---\nname: frely\ndescription: Use when the user wants to work with their Frely account or the Frely marketplace through the frely CLI (credits, API keys, plans, orFix: Namespace tool names and keep tool descriptions literal; no instructions to the agent inside them.
AST04
LOW
Instructs the agent to modify its persistent memory or instruction filesdist/agent-help.d.ts:150 · 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 filereadonly purpose: "Send the complete relevant user request to the installed Agent through model-scoped MCP. Usage may be billed. The call runs in a background worker and is recorded on this computer (Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
MEDIUM
URL using raw IP addressdist/runtime/mcp.js:47 · URL using raw IP address — may bypass domain-based filteringexport const LOCAL_MODELS_TOOL = tool("local_models", "Use a model server running on this device (Ollama, LM Studio, vLLM, llama.cpp, mltf) through Frely. action=list probes loopback OpenAI-compatibleFix: Replace encoded or assembled strings with plain literals and remove undeclared network calls.
AST07
MEDIUM
File permission modification commanddist/app-manager.js:284 · File permission modification command — agent changes file ownership/permissionsd.log("Warning: could not mark the AppImage executable; run chmod +x manually.");Fix: Request the narrowest permission that works; replace wildcards with the exact paths or hosts.
AST05
MEDIUM
Process kill commanddist/agent-help.d.ts:405 · Process kill command — agent can terminate processesreadonly usage: "frely kill <device> <id>";Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05

Cost to the agent

Instructions loaded
≈59 tok
1 file · 81 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

No advisories in OSV for frely-cli@0.23.34 as of 8d ago. This is the package itself, not its dependencies.

What would make this Verified

12 points to 80 · weights: behavior 45%, static 25%, prompt 15%, publisher 15%
  1. Reads credential paths from the home directory≈ +9 on the totalStop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
  2. Unclaimed publisher≈ +8 on the totalClaim frelyhq: a verified publisher gets +50 on publisher trust. It is free and usually instant with GitHub sign-in.
  3. Privileged sudo command≈ +4 on the totalBuild commands from fixed arguments; do not interpolate untrusted strings into a shell.
  4. 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.
  5. Outbound HTTP to raw IP address≈ +4 on the totalReplace encoded or assembled strings with plain literals and remove undeclared network calls.
  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 npm, then queue it here. Not your skill? Claim the handle to get verdict changes by email.Claim frelyhqPropose a patch to the maintainer