github-fetcher@0.2.1
VERIFIED· install onlyPublisher claims: "Enables AI coding agents to read GitHub repositories, files, commits, issues, pull requests, releases, Actions, and search results through 18 read-only MCP tools. It reuses existing credentials, routes around unreliable networks, and caches responses on disk to stay within rate limits." 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
GH_TOKENGITHUB_TOKENConfiguration, not credentials: GITHUB_CACHE, GITHUB_CACHE_DIR, GITHUB_MCP_EXPOSE_IDENTITY, GITHUB_MCP_LOG, GITHUB_MCP_MAX_FILE_BYTES, GITHUB_MCP_TIMEOUT_MS, GITHUB_PROXY, GITHUB_PROXY_MODE- Where it talks to
- no vendor host named in the codeAlso githubusercontent.com, com.proxy — 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, com.proxy as well as its own vendor. The guard injects GH_TOKEN, GITHUB_TOKEN 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 88/100 (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
//* One bad repo must not kill the batch: a GithubError becomes an error itemFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.const INSTALL = "npx -y @kurvcygnus/github-fetcher@latest";Fix: Pin versions and sources; vendor anything fetched at install time.//! chmod 0o000 does not make files unreadable on Windows (it only togglesFix: Request the narrowest permission that works; replace wildcards with the exact paths or hosts.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.