squeze@2.2.1
VERIFIED· install onlyPublisher claims: "An MCP server that turns a task, error or stack trace into a few verbatim, line-cited source excerpts from a local repository index, staying inside a token budget the caller chooses. It also exposes tools to expand a cited range, outline or importance-rank a repository, and explore an import/reference graph, so coding agents can answer questions without reading whole files and without network or model calls." Observed in sandbox: no network, touches nothing outside the project, writes no memory.
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
RSQ_TOKENIZERConfiguration, not credentials: GO_TRUTH, GRAPH_EVAL_PY_STDLIB, REPOSQUEEZE_BENCH_EMBEDDING, REPOSQUEEZE_CACHE_DIR, REPOSQUEEZE_EXACT_STATS, REPOSQUEEZE_LARGE_THRESHOLD, REPOSQUEEZE_LIVE_MODEL, REPOSQUEEZE_MAX_CANDIDATES, REPOSQUEEZE_REFRESH_INDEX, REPOSQUEEZE_TIMINGS, REPOSQUEEZE_WORKER_FILE, REPOSQUEEZE_WORKERS, RSQ_FEATURES, RSQ_LAB, RSQ_MAX_LOAD, RSQ_PARSER_RICH, UV_THREADPOOL_SIZE- Where it talks to
- no vendor host named in the codeAlso githubusercontent.com — 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 githubusercontent.com as well as its own vendor. The guard injects RSQ_TOKENIZER only into requests to the host you bind (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 (1 scenario; nothing executable in the bundle ran; the trace covers the install step only) on 2026-11-11 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 · 0 s · 1 scenarios · 0 deviationsStatic findings
if (lower === '.env' || lower.startsWith('.env.') || lower.endsWith('.env')) return true;Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.…st PLACEHOLDER_WORDS = /your[-_ ]?|<|>|\$\{|\$\(|\{\{|\}\}|%\(|%s|%\{|process\.env|os\.environ|getenv|changeme|change[-_]me|example|sample|dummy|placeholder|x{6,}…Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.const secrets = /(^|\/)(?:\.env(?:\..*)?|\.npmrc|\.pypirc|\.netrc|id_(?:rsa|ed25519)|credentials(?:\.[^/]*)?|secrets?(?:\.[^/]*)?|[^/]*\.(?:pem|key|p12|pfx|keystore))$/i;Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.'.npmrc', '.pypirc', '.netrc', '_netrc', '.htpasswd', '.pgpass', '.git-credentials', '.dockercfg',Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.const kill = (): void => {Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell./** True for files that normally hold credentials; templates such as `.env.example` are excluded. */Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.…ols=','--disable-builtin-mcps','--no-custom-instructions','--no-ask-user','--no-auto-update','--max-ai-credits','30','--usage-output-file',usagePath,'--log-level','none','--silent'],{cwd:work,encoding:'utf8',timeout:180000,maxBuffer:2*1024…Fix: Put hosts, commands and strings in plain source. Decoding at runtime looks identical to malware and costs points on its own.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
Vulnerability advisories (OSV) cover npm and PyPI packages; this registry has no advisory database.