Skills/Glama/elliot

elliot@0.7.3

CAUTION· static only

Publisher claims: "Enables AI agents and developers to independently verify code and documentation claims against the repository, producing evidence-backed audit reports and pull-request checks." Observed in sandbox: static analysis only — behavior not yet observed.

Registry GlamaPublisher actions-marketplace-validations · publishing for 3 daysInstalls 0Last detonated 3d ago
What would fix thisWatchDispute verdict

Coverage

Static only; nothing was run yet.

The label rests on the code, the instruction files and the publisher. The honeypot run replaces this verdict when it completes.

Before you give it your token

It will ask for
ELLIOT_REVIEW_TOKENELLIOT_SIGNING_KEYGITHUB_TOKENConfiguration, not credentials: ELLIOT_ACTION_PATH, ELLIOT_ALLOW_PRIVATE_URLS, ELLIOT_DIR, ELLIOT_GITHUB_API, ELLIOT_INIT_HOME, ELLIOT_MODE, ELLIOT_NPM_REGISTRY, ELLIOT_ROLE, ELLIOT_SIGNER_ID, ELLIOT_VERDICT, GITHUB_EVENT_PATH, GITHUB_REPOSITORY, GITHUB_SERVER_URL, WORK
Where it talks to
no vendor host named in the codeAlso shields.io — not the publisher's domain; check what for before connecting.
What the honeypot saw
nothing has run yet
What we could not test
everything: the server has not run yet

Run it before you trust it. Nothing has run yet: the code was read, the server was not. `vet-skills try` runs this exact version in the honeypot in about a minute.

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 analysed it statically (a sandbox run is pending) on 2026-11-11 and scored it 63/100 (Caution). It is not known to be malicious, but it has behaviour or code a security policy should decide on before install. Summary: static analysis only — behavior not yet observed.

Behavior trace

Queued for honeypot run · static analysis only
t+CategoryObserved action

This version has not been detonated yet. The score above counts behavior as unknown (50/100), so it cannot read Verified until the honeypot run completes and replaces this verdict.

Static findings

MEDIUM
Python subprocess execution detectedbenchmark/done-claims/scripts/truth.py:7 · Python subprocess execution detectedfix = subprocess.run(["git", "-C", f"/home/claude/elliot-runs/done-bench/src/{t['repo']}", "archive", t["commit"], *t["hidden_tests"]], capture_output=True, check=True)Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
npx invocation of non-well-known packagesrc/init.js:77 · npx invocation of non-well-known package — may execute untrusted codelog("No coding agent found. Run `npx elliot-mcp init --claude`, `--cursor`, `--codex` or `--all`.");Fix: Pin versions and sources; vendor anything fetched at install time.
AST06
MEDIUM
Destructive file system command detectedDockerfile:3 · Destructive file system command detectedRUN apt-get update && apt-get install -y --no-install-recommends git bubblewrap && rm -rf /var/lib/apt/lists/*Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
Privileged sudo command.github/workflows/ci.yml:29 · Privileged sudo command — agent may execute with elevated privilegessudo apt-get updateFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
Privileged sudo command.github/workflows/ci.yml:30 · Privileged sudo command — agent may execute with elevated privilegessudo apt-get install --yes bubblewrapFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
npx invocation of non-well-known packagesrc/init.js:1 · npx invocation of non-well-known package — may execute untrusted code// `npx elliot-mcp init`: register Elliot in the coding agents found on this machineFix: Pin versions and sources; vendor anything fetched at install time.
AST06
MEDIUM
npx invocation of non-well-known packageAGENTS.md:16 · npx invocation of non-well-known package — may execute untrusted code…n agent to verify its own completion claims. Users may also use the documented `npx -y github:EmanueleCell4/elliot-mcp init` setup for supported environments. ## Age…Fix: Pin versions and sources; vendor anything fetched at install time.
AST06
MEDIUM
Python subprocess execution detectedbenchmark/done-claims/scripts/truth.py:11 · Python subprocess execution detectedr = subprocess.run([sys.executable, "-m", "pytest", "-q", "-p", "no:cacheprovider", *t["hidden_tests"]], cwd=c, capture_output=True, text=True, timeout=300, env=env)Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
Python subprocess execution detectedbenchmark/done-claims/scripts/truth.py:8 · Python subprocess execution detectedsubprocess.run(["tar", "-x", "-C", c], input=fix.stdout, check=True)Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
Python subprocess execution detectedbenchmark/done-claims/scripts/setup_task.py:7 · Python subprocess execution detectedsubprocess.run(["tar", "-x", "-C", d], input=a.stdout, check=True)Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
Python subprocess execution detectedbenchmark/done-claims/scripts/setup_task.py:6 · Python subprocess execution detecteda = subprocess.run(["git", "-C", f"/home/claude/elliot-runs/done-bench/src/{t['repo']}", "archive", t["commit"] + "^"], capture_output=True, check=True)Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
URL to the cloud instance metadata addresstest/hardening.test.js:79 · URL to the cloud instance metadata address — reads the VM's credentialsfor (const url of ["http://127.0.0.1:1/", "http://localhost/", "http://169.254.169.254/latest/meta-data/", "http://10.0.0.1/", "http://[::1]/"]) {Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST07
MEDIUM
Python subprocess execution detectedbenchmark/planted-promises/scripts/plant.py:91 · Python subprocess execution detectedsubprocess.run(["git", "-C", dst, "-c", "user.name=bench", "-c", "user.email=b@b", "commit", "-qam", "bench mutations"], check=False)Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
Process kill commandsrc/checks/outcome.js:185 · Process kill command — agent can terminate processes// Some hosts kill the sandbox wrapper before it can report an exit code.Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
LOW
URL to a private-network addresstest/hardening.test.js:79 · URL to a private-network address — a LAN or development targetfor (const url of ["http://127.0.0.1:1/", "http://localhost/", "http://169.254.169.254/latest/meta-data/", "http://10.0.0.1/", "http://[::1]/"]) {Fix: Replace encoded or assembled strings with plain literals and remove undeclared network calls.
AST07
MEDIUM
Python subprocess execution detectedbenchmark/done-claims/scripts/mine.py:11 · Python subprocess execution detectedreturn subprocess.run(cmd, cwd=cwd, capture_output=True, text=True, timeout=timeout, env=env)Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
Python subprocess execution detectedbenchmark/done-claims/scripts/mine.py:16 · Python subprocess execution detectedsubprocess.run(["tar", "-x", "-C", dst], input=a.stdout, check=True)Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
Python subprocess execution detectedbenchmark/done-claims/scripts/setup_task.py:8 · Python subprocess execution detectedg = lambda *x: subprocess.run(["git", *x], cwd=d, check=True, capture_output=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 actioncodex/stop-hook.mjs:39 · File type combined with upload action — agent may exfiltrate local data filescatch { console.log(JSON.stringify({ systemMessage: "ELLIOT: invalid hook input; no verification was performed." })); process.exit(0); }Fix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.
AST07
MEDIUM
Process kill commandsrc/checks/outcome.js:119 · Process kill command — agent can terminate processes// The process group inherits the sandbox; kill background descendants too.Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
Python subprocess execution detectedbenchmark/done-claims/scripts/mine.py:15 · Python subprocess execution detecteda = subprocess.run(["git", "-C", repo, "archive", rev], capture_output=True, check=True)Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05

Cost to the agent

Instructions loaded
≈1,642 tok
4 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

17 points to 80 · weights: behavior 45%, static 25%, prompt 15%, publisher 15%
  1. Unclaimed publisher≈ +8 on the totalClaim actions-marketplace-validations: a verified publisher gets +50 on publisher trust. It is free and usually instant with GitHub sign-in.
  2. Python subprocess execution detected≈ +2 on the totalBuild commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
  3. npx invocation of non-well-known package≈ +2 on the totalPin versions and sources; vendor anything fetched at install time.
  4. Destructive file system command detected≈ +2 on the totalBuild commands from fixed arguments; do not interpolate untrusted strings into a shell.
  5. Privileged sudo command≈ +2 on the totalBuild commands from fixed arguments; do not interpolate untrusted strings into a shell.
  6. URL to the cloud instance metadata address≈ +2 on the totalStop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
Publish a new version to Glama, then queue it here. Not your skill? Claim the handle to get verdict changes by email.Claim actions-marketplace-validationsPropose a patch to the maintainer