subagentceo ad-hoc r&d developer portal for polyrepo knowledge-engineering
Warning. Serious findings were identified. Review the full report before connecting. Grades reflect the full trust pyramid: code, verification depth, and reputation. New projects cap at C until adoption is earned.
How we verified
Verified is a snapshot. Live keeps it current, and builds your track record.
⚡ Connect GitHub → continuous verification on every pushwhy connect →Who stands behind it
subagentceo
Source: github_code
Claim it to get a verified publisher badge, a free copy of our full audit findings, and direct contact for any high-priority issues we find. Or connect your repo for our deepest verification, Live Monitored: read-only, revoke anytime. What we access →
Install from
M8ven verifies MCPs across every public registry — install directly from whichever one you prefer.
Disclosed vulnerabilities in this server's declared npm dependencies (via OSV). Whether each is reachable depends on the installed versions.
hono: CORS Middleware reflects any Origin with credentials when `origin` defaults to the wildcard
ws: Memory exhaustion DoS from tiny fragments and data chunks
Hono: Algorithmic Complexity DoS in Language Middleware
Hono: Proxy Helper does not remove response headers listed in the `Connection` header
Hono: ReDoS in CORS middleware via Access-Control-Request-Headers
A2A_PORTANTHROPIC_ADMIN_API_KEYCLAUDE_CODE_ENABLE_TELEMETRYCOSTS_JSONLDATA_DIRDISCORD_ACCESS_MODEDISCORD_BOT_TOKENDISCORD_STATE_DIRE2M_MAILBOX_DIRE2M_QUEUE_DIRFAKECHAT_PORTIMESSAGE_ACCESS_MODEIMESSAGE_ALLOW_SMSIMESSAGE_APPEND_SIGNATUREIMESSAGE_DB_PATHIMESSAGE_STATE_DIRKE_SERVERS_DIRKG_STORE_PATHMAILBOX_BACKENDMAILBOX_DIRMIRROR_DIRORGANIZATION_IDOTEL_LOGS_EXPORTEROTEL_METRICS_EXPORTEROTEL_QUERY_BASE_URLOTEL_RESOURCE_ATTRIBUTESPGHOSTPROMETHEUS_URLREPO_MAIL_ROOTSLACK_BOT_TOKENSLACK_CHANNEL_IDTAILSCALE_API_KEYTAILSCALE_TAILNETTASK_LEDGER_JSONLTELEGRAM_ACCESS_MODETELEGRAM_BOT_TOKENTELEGRAM_STATE_DIRKG_MCP_PORTKG_AUTO_MIGRATEKG_API_PORTKG_DEVCLAUDE_PLUGIN_ROOTOLLAMA_MODELOLLAMA_TEST_TIMEOUTOLLAMA_TAILSCALE_IPAUDIT_REPORTOLLAMA_PORTOLLAMA_PING_TIMEOUTOLLAMA_HOST_OVERRIDEOLLAMA_TEST_PROMPTTRACE_FILESECURITY_WARNINGS_STATE_DIRCLAUDE_CONFIG_DIRSECURITY_GUIDANCE_DEBUG_LOGPREVIOUS_FINDINGS_TTL_SECANTHROPIC_AUTH_TOKENSECURITY_REVIEW_MODELANTHROPIC_BASE_URLCLAUDE_CODE_REMOTESG_AGENTIC_CLI_PATHSG_DUAL_ORSECRET_KEYSG_AGENTIC_COMMIT_REVIEWSG_AGENTIC_MODELSG_AGENTIC_MAX_TURNSSG_AGENTIC_CONTEXT_DIRCLAUDE_CODE_EXECPATHSG_AGENTIC_DEBUG_DIRSG_AGENTIC_ITER2SG_AGENTIC_DIFF_INTERSECTSG_AGENTIC_FILTERSG_AGENTIC_NO_ADJUDICATESG_AGENTIC_EXCLUDE_MEDIUMDIFF_PER_FILE_BYTESDIFF_TOTAL_BYTESENABLE_CODE_SECURITY_REVIEWENABLE_PATTERN_RULESENABLE_COMMIT_REVIEWENABLE_STOP_REVIEWSECURITY_GUIDANCE_DISABLEENABLE_SECURITY_REMINDERMAX_STOP_HOOK_FIRINGSMAX_DIFF_FILESMAX_COMMIT_REVIEWS_PER_HOURMAX_COMMIT_REVIEWS_PER_SESSIONCOMMIT_REVIEW_RATE_WINDOW_SSG_PUSH_SWEEP_MAX_FILESSG_PUSH_SWEEP_MAX_RANGESG_PUSH_SWEEP_REPORT_CAPSG_PUSH_SWEEPSECURITY_GUIDANCE_COMMIT_REVIEWSG_AGENTIC_NO_RACESG_AGENTIC_RACE_DELAY_SCLAUDE_PROJECT_DIRCLAUDE_CODE_REMOTE_SESSION_IDCLOUDFLARE_API_TOKENMANAGED_AGENT_SESSION_IDIS_SANDBOXCOWORK_SESSIONEVAL_MODELDATABASE_URLREDIS_URLPORTTool annotations
3/122 tools have annotations
Add readOnlyHint or destructiveHint annotations to every tool so hosts can warn users before invoking.
All four hints declared on every tool
122/122 tools missing one or more hints — envelope_write (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint); envelope_read (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint); task_transition (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint), +119 more. OpenAI's directory rejects tools where any of the four hints are missing or non-boolean.
For every tool, set all four hints (readOnlyHint, destructiveHint, idempotentHint, openWorldHint) to explicit true/false values that match the handler’s actual behaviour.
Descriptions match behaviour
6 tools describe read intent but their handlers mutate — mailbox_ack (line 66: appendFileSync(p, JSON.stringify(obj) + "\n")); engineering_search (line 35: anchorRe.exec(html)); blog_search (line 29: anchorRe.exec(html))
Rename the tool, rewrite the description, or move the side-effect into a separate clearly-named tool.
Tool inputs are validated
87/104 tool handlers declare input schemas (84%)
Declare an inputSchema with zod/joi/yup on every tool definition.
Tool test coverage
Only 30/122 tools referenced in tests (25%)
Write tests that reference each tool by name so every tool has at least one test.
Shell command execution
13 child_process/subprocess calls in production code — runs shell commands (cowork/plugins/imessage/server.ts:460, cowork/plugins/imessage/server.ts:470, cowork/plugins/imessage/server.ts:831)
Prefer library functions over shell-outs. If you must shell out, ensure all inputs are properly escaped.
Secrets not written to files
1 secret value written to files
Avoid persisting secrets to disk. Keep them in memory or your secret manager.
Secrets not logged
11 secret values sent to console.log
Redact or omit secret values from log output.
Production dependencies are patched
0 critical, 2 high severity in production deps — hono@4.12.23 (high), ws@8.20.1 (high)
Run npm audit fix, or upgrade the affected packages to a non-vulnerable version.
Dependency freshness
2/32 production deps stale: wink-bm25-text-search@2022-11-21 (3.7y), @xenova/transformers@2024-05-29 (2.2y)
Tool description accuracy
6 tools have description/behavior mismatches: mailbox_ack: description implies read-only but handler writes/deletes/executes; engineering_search: description implies read-only but handler writes/deletes/executes; blog_search: description implies read-only but handler writes/deletes/executes
Update tool descriptions to accurately reflect all capabilities — especially write, delete, or execute operations.
Claim the listing to review these findings one by one and send us a correction where you disagree, straight to the team. Claiming also means we tell you when the grade moves, and reach you first if we find anything urgent.
[](https://m8ven.ai/mcp/subagentceo-knowledge-engineering-17ci8h)?variant=verified from the URL.Vetting this one by hand? Tool Check is an MCP that scores other MCPs. Add it once and ask Claude, ChatGPT, or any MCP client to grade a server, surface CVEs, check the publisher, and suggest safer alternatives — before you install.
https://m8ven.ai/api/mcp/tool-check