repowise@0.61.0
VERIFIED· not startedPublisher claims: "The codebase intelligence layer for your AI coding agent — dependency graph, git history, dead code, decisions, and code health, exposed over MCP" Observed in sandbox: no network, touches nothing outside the project, writes no memory.
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: 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
REPOWISE_API_KEYREPOWISE_CORS_ALLOW_CREDENTIALSREPOWISE_DATABASE_URLConfiguration, not credentials: COLUMNS, REPOWISE_CACHE_HMAC_KEY, REPOWISE_CACHE_KEY_PATH, REPOWISE_CHANGELOG, REPOWISE_CORS_ORIGINS, REPOWISE_DB_URL, REPOWISE_FTS_DF_CEILING, REPOWISE_HOST, REPOWISE_REASONING- Where it talks to
- repowise.dev (its own)Also schemastore.org — not the publisher's domain; check what for before connecting.
- What we saw when it ran
- no credential files read · no network
- What we could not test
- server startup · the tool list · tool behavior
Connect it with a scoped credential, under the guard, and read the third-party hosts first. The code names schemastore.org as well as its own vendor. The guard injects REPOWISE_API_KEY, REPOWISE_CORS_ALLOW_CREDENTIALS, REPOWISE_DATABASE_URL only into requests to repowise.dev (and its subdomains) and refuses the rest.
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 2026-11-21 and scored it 81/100 (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 · 1 s · 2 scenarios · 0 deviationsStatic findings
return subprocess.check_output(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.out = subprocess.run(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.subprocess.Popen(argv, creationflags=_WINDOWS_FLAGS, **kwargs) # type: ignore[call-overload]Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.#: NOT ``IGNORED_FIRST_TOKENS``, which also holds rm/mv/chmod/kill — thoseFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.subprocess.Popen( # type: ignore[call-overload]Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.".env",Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.("fd", re.compile(r"(?:^|\s)(?:-[xX]|--exec(?:-batch)?)(?:\s|$)")),Fix: Put hosts, commands and strings in plain source. Decoding at runtime looks identical to malware and costs points on its own.("find", re.compile(r"(?:^|\s)-(?:exec(?:dir)?|ok(?:dir)?|delete)(?:\s|$)")),Fix: Put hosts, commands and strings in plain source. Decoding at runtime looks identical to malware and costs points on its own.# Both halves read ``<repo>/.repowise/.env`` themselves rather than theFix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.result = subprocess.run(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.result = subprocess.run(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out."""Fetch editor data and write AGENTS.md."""Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.subprocess.check_call(["git", *args], cwd=repo, stderr=subprocess.DEVNULL)Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.return subprocess.run(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.subprocess.Popen(argv, start_new_session=True, **kwargs) # type: ignore[call-overload]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. 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 repowise@0.61.0 as of 46 min ago. This is the package itself, not its dependencies.