Skills/Glama/keen-mcp

keen-mcp@r1

CAUTION· install only

Publisher claims: "Enables AI agents to search and invoke 1,939 Atlassian automation tools across Jira, Confluence, Bitbucket, Admin, Assets, and more, with cached reads and JSON-RPC over stdio. It helps agents find tools without calling Atlassian and execute operations while reducing rate-limit pressure." Observed in sandbox: no network, touches nothing outside the project, writes no memory.

Registry GlamaPublisher imogenlabs · publishing for 3 daysInstalls 0Last detonated 3d 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
JIRA_CLOUD_PLATFORM_PASSWORD or --no-authConfiguration, not credentials: JIRA_CLOUD_PLATFORM_USERNAME, TEMPLATE_VARS
Where it talks to
no vendor host named in the codeAlso atlassian.com, atlassian.net — 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 with a scoped credential, under the guard, and read the third-party hosts first. The code names atlassian.com, atlassian.net as well as its own vendor. The guard injects JIRA_CLOUD_PLATFORM_PASSWORD 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 keen-mcp@r1 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 2026-11-11 and scored it 78/100 (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; Auto-update or dynamic fetch configuration; Privileged sudo command. 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
Python subprocess execution detectedscripts/regen/graphql.py:36 · Python subprocess execution detectedout = subprocess.run(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
Python subprocess execution detectedscripts/mcp-check.py:66 · Python subprocess execution detectedout = subprocess.run([keen, *args, "--json"], capture_output=True, text=True)Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
File type combined with upload actioninternal/cli/root.go:163 · File type combined with upload action — agent may exfiltrate local data filesrootCmd.PersistentFlags().BoolVar(&flags.csv, "csv", false, "Output as CSV (table and array responses)")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 detectedscripts/regen/deprecated.py:77 · Python subprocess execution detectedsubprocess.run(["gofmt", "-w", str(OUT)], check=True)Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
HIGH
Privileged sudo commandSKILL.md:30 · Privileged sudo command — agent may execute with elevated privilegessudo dnf install ./keen_linux_amd64.rpm # Fedora, RHEL (arm64: keen_linux_arm64.rpm)Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
Python subprocess execution detectedscripts/regen/specdiff.py:78 · Python subprocess execution detectedif subprocess.run([sys.executable, str(REPO / "scripts" / "regen" / "graphql.py"), "--check"]).returncode:Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
HIGH
Auto-update or dynamic fetch configurationspecs/marketplace.json:1 · Auto-update or dynamic fetch configuration — agent may load new code at runtime…"End-User Data type your app stores"}}}},"AddonVersionDeployment":{"required":["autoUpdateAllowed","cloud","connect","dataCenter","permissions","server"],"type":"object","properties":{"server":{"type":"boolean","description":"True if the v…Fix: Pin versions and sources; vendor anything fetched at install time.
AST06
MEDIUM
Python subprocess execution detectedscripts/regen/check.sh:28 · Python subprocess execution detectedr = subprocess.run([keen, *c.split(), "--help"], capture_output=True, text=True)Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
Python subprocess execution detectedscripts/regen/specdiff.py:25 · Python subprocess execution detectedout = 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 actionspecs/admin-orgs.json:1 · File type combined with upload action — agent may exfiltrate local data files…d/jira/platform/basic-auth-for-rest-apis/).**\nIf you don’t have Jira, export a .csv of the user list. Learn how to [export users from a site](https://support.atlassian.com/organization-administration/docs/export-users-from-a-site/).","sch…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 detectedscripts/mcp-check.py:183 · Python subprocess execution detectedrun = subprocess.run(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
Python subprocess execution detectedscripts/regen/deprecated.py:28 · Python subprocess execution detectedout = subprocess.run(["bash", "-c", 'source scripts/regen/config.sh && printf "%s\\n" "${SPECS[@]}"'],Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
HIGH
Privileged sudo commandSKILL.md:27 · Privileged sudo command — agent may execute with elevated privilegessudo apt install ./keen_linux_amd64.deb # Debian, Ubuntu (arm64: keen_linux_arm64.deb)Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
Python subprocess execution detectedscripts/mcp-check.py:30 · Python subprocess execution detectedself.p = subprocess.Popen([binary], stdin=subprocess.PIPE, stdout=subprocess.PIPE,Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
Python subprocess execution detectedscripts/regen/graphql.py:104 · Python subprocess execution detectedsubprocess.run(["gofmt", "-w", str(TABLE)], check=True)Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
File type combined with upload actionspecs/compass.json:1 · File type combined with upload action — agent may exfiltrate local data files…file with package dependency information. Currently, we only accept package-lock.json files that are below 2MB. \\\n\\\nThe baseSourceUrl should be a url link to your lock file, ideally with \"#lines-\" appended at the end, if from Bitbuck…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 actionspecs/confluence.json:1 · File type combined with upload action — agent may exfiltrate local data files… 'multipart/form-data' is defined in [RFC 7578](https://www.ietf.org/rfc/rfc7578.txt).\nMost client libraries have classes that make it easier to implement\nmultipart posts, like the [MultipartEntityBuilder](https://hc.apache.org/httpcompo…Fix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.
AST07
LOW
Authorization escalation languagespecs/admin-orgs.json:1 · Authorization escalation language · informational: not an instruction file…g a user to the org-admins group through this API no longer grants organization admin access. To assign organization admin access, use the [Assign organization-level role e…Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01

Cost to the agent

Instructions loaded
≈34,698 tok
2 files · 80 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

2 points to 80 · weights: behavior 45%, static 25%, prompt 15%, publisher 15%
  1. Unclaimed publisher≈ +8 on the totalClaim imogenlabs: 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. Auto-update or dynamic fetch configuration≈ +4 on the totalPin versions and sources; vendor anything fetched at install time.
  4. Python subprocess execution detected≈ +2 on the totalBuild commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
  5. 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.
Publish a new version to Glama, then queue it here. Not your skill? Claim the handle to get verdict changes by email.Claim imogenlabsPropose a patch to the maintainer