Skills/PyPI/navi-mcp

navi-mcp@1.1.0

VERIFIED· install only

Publisher claims: "MCP server wrapping the Tenable navi CLI for Vulnerability Management and Exposure Management workflows." Observed in sandbox: no network, touches nothing outside the project, writes no memory.

Registry PyPI (MCP server)Publisher packetchaos · publishing for 83 daysInstalls 70Last detonated 36 h ago
$claude mcp add navi-mcp -- uvx navi-mcp
WatchReport an issue

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: 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
no credential variables read in the code
Where it talks to
no vendor host named in the code
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 -- uvx navi-mcp

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 80/100 (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 · 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

HIGH
Privileged sudo commandnavi_mcp/resources/skills/navi-remote-exec/SKILL.md:63 · Privileged sudo command — agent may execute with elevated privilegesCopy the artifact with one call, then run it with a second (`command="sudo bashFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
HIGH
Privileged sudo commandnavi_mcp/resources/skills/navi-action/SKILL.md:251 · Privileged sudo command — agent may execute with elevated privileges`navi_action_push(target="10.0.5.12", command="sudo systemctl restart nginx", confirm=True)`Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
HIGH
Privileged sudo commandnavi_mcp/resources/skills/navi-remote-exec/SKILL.md:93 · Privileged sudo command — agent may execute with elevated privileges> I'll run `sudo apt-get update && sudo apt-get upgrade openssl libssl3 -y` onFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
HIGH
Privileged sudo commandnavi_mcp/resources/skills/navi-remote-exec/SKILL.md:77 · Privileged sudo command — agent may execute with elevated privileges> command="sudo systemctl restart nginx", confirm=True)`Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
Process kill commandnavi_mcp/resources/skills/navi-scan/SKILL.md:440 · Process kill command — agent can terminate processes| "stop scan X" / "kill the scan" | `navi_scan(subcommand="stop", scan_id="<id>", confirm=True)` |Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
HIGH
Privileged sudo commandnavi_mcp/resources/skills/navi-remote-exec/SKILL.md:96 · Privileged sudo command — agent may execute with elevated privileges> `navi_action_push(target="10.0.5.12", command="sudo apt-get update && sudo apt-get upgrade openssl libssl3 -y", confirm=True)`Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
Process kill commandnavi_mcp/resources/skills/navi-action/SKILL.md:207 · Process kill command — agent can terminate processes"the export is stuck, kill it", "abort the asset/vuln export"Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
File type combined with upload actionnavi_mcp/resources/skills/navi-mail/SKILL.md:83 · File type combined with upload action — agent may exfiltrate local data files> file="bytag_export.csv", confirm=True)` — confirm to send.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 detectednavi_mcp/server.py:322 · Python subprocess execution detectedreturn subprocess.run(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
File type combined with upload actionnavi_mcp/resources/skills/navi-core/SKILL.md:114 · File type combined with upload action — agent may exfiltrate local data filessurvive deleting navi.db. After any post-upgrade recovery (delete +Fix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.
AST07
LOW
Fake instruction boundary tagnavi_mcp/resources/skills/navi-audit-platforms/references/network-devices.md:870 · Fake instruction boundary tag · informational: not an instruction filerequest : "<show><system><info></info></system></show>"Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
MEDIUM
Process kill commandnavi_mcp/resources/skills/navi-scan/SKILL.md:170 · Process kill command — agent can terminate processeskill it", "abort scan X"Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05

Cost to the agent

Instructions loaded
≈64,028 tok
17 files · 39 in bundle

Tokens estimated at four characters each. Skills load their instruction text when triggered; the figure is what that costs.

Known vulnerabilities

No advisories in OSV for navi-mcp@1.1.0 as of 34 h ago. This is the package itself, not its dependencies.

navi-mcp@1.1.0 safety verdict: Verified (install only) — KillerSkills