resume-agent
Fork-ready A2A + MCP professional agent — employer AI systems query your profile, OEP domain verification, private job-hunt MCP. Deploy your own in minutes.
Caution. Specific findings reduced this grade. They are listed on the page. 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
yuens1002
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
The grade above is for the source repository. Registries can serve a different version, so we mark the ones we were not able to read.
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
Hono: Path traversal in toSSG() allows writing files outside the output directory
Vercel’s AI SDK's filetype whitelists can be bypassed when uploading files
Hono missing validation of cookie name on write path in setCookie()
Hono: app.mount() strips mount prefix using undecoded path, causing incorrect routing for percent-encoded paths
AI_MODELALLOWED_ORIGINSAPI_KEYpublic_profile table: read-only, no auth required, rate-limited to 30 req/min per IP — bypassed for requests carrying a valid Authorization: Bearer <> headerAUTH_MODE/resume endpoint: when =key, requires Authorization: Bearer <key> header; when AUTH_MODE=open (default in .env.example), it is publicly accessibleHIDE_FROM_PROJECTSIP_HASH_SALTJWT_SECRETMATCH_MODELOAUTH_CLIENT_IDyour OAUTH_CLIENT_ID env var valueOAUTH_CLIENT_SECRETyour OAUTH_CLIENT_SECRET env var valueOBSERVATIONS_TOPICSOPENROUTER_API_KEYYour OpenRouter API keyOPEN_BRAIN_KEYPROVIDER_HOMEPAGEThis card uses provider.organization and provider.url to satisfy the registry. The env var maps to provider.url — it must be set or the registry will reject the card.PUBLIC_URLQR_TARGET_URLQUERY_THOUGHTS_THRESHOLDRESUME_MODELRESUME_MODEL_BSUPA_PROJECT_URLYour Supabase project URLPORTSUPA_SERVICE_ROLETool annotations
No tools have read-only/destructive annotations
Add readOnlyHint or destructiveHint annotations to every tool so hosts can warn users before invoking.
All four hints declared on every tool
19/19 tools missing one or more hints — search_thoughts (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint); list_thoughts (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint); thought_stats (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint), +16 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.
Destructive tools are labelled
8 tools perform destructive updates without destructiveHint — update_profile overwrites at line 302 (supabase); upsert_project overwrites at line 380 (supabase); upsert_publication overwrites at line 429 (supabase)
Add destructiveHint:true to any tool whose handler calls .delete(), .upsert(), .update(), unlink, rm, DELETE, DROP, REPLACE INTO, or any operation that overwrites existing data.
Descriptions match behaviour
1 tool describes read intent but its handler mutates — capture_thought (line 465: supabase.from('thoughts').insert({)
Rename the tool, rewrite the description, or move the side-effect into a separate clearly-named tool.
Tool test coverage
14/19 tools referenced in tests (74%)
Write tests that reference each tool by name so every tool has at least one test.
Secrets not logged
2 secret values sent to log
Redact or omit secret values from log output.
Production dependencies are patched
0 critical, 1 high severity in production deps — hono@4.12.9 (high), hono@4.12.9 (medium)
Run npm audit fix, or upgrade the affected packages to a non-vulnerable version.
Tool description accuracy
capture_thought: 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/yuens1002/resume-agent)?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