Connect your AI agents to GitHub — manage repos, issues, PRs, workflows, and more
Source not yet analyzed — this grade rests on attested signals (CVEs, supply-chain) only. It is a floor: reading the code could raise it, not lower it.
- capability exposure inferred + 35
- tool safety inferred + 25
- trust mitigators mixed − 8
inferred mixed
The A–E grade is our heuristic synthesis — a "review this" prompt, not a verdict. Each factor is tagged by what backs it: attested (a verifiable record), reported (a third party's claim), or inferred (our own heuristic, e.g. permissions). See methodology.
graded 41s ago · see ecosystem CVEs →
- C · 57 → C · 52
- D · 62 → C · 57
- C · 57 → D · 62
No known CVEs for this server.
- high exfiltration combo run_secret_scanning
single tool reads + sends: fs, net, secrets
- high toxic flow (lethal trifecta) github_support_docs_search
single tool reads private data, ingests untrusted content, and reaches the network: net, db, untrusted
- medium exfiltration combo add_comment_to_pending_review
single tool reads + sends: fs, net
- medium purpose mismatch create_or_update_file
benign-looking name carries shell
- medium purpose mismatch get_copilot_space
benign-looking name carries shell
- medium tool poisoning label_write
cross-tool-steering: "use the 'update_issue' tool"
- medium tool poisoning list_pull_requests
cross-tool-steering: "use the search_pull_requests tool"
- low exfiltration combo github_support_docs_search
single tool reads + sends: net, db, untrusted
- low purpose mismatch get_team_members
benign-looking name carries secrets
- low purpose mismatch get_teams
benign-looking name carries secrets
[](https://mcpobservatory.com/servers/smithery:github/security) Heuristic, inferred signals — false positives (legitimately powerful tools, forks, language ports) are expected. Treat each as "review this", not a verdict. See the ecosystem-wide picture on the security hub, or the fleet security of github.