MCP, MCP server
banrepco_mcp
This project implements a Model Context Protocol (MCP) server for the Bank of the Republic of Colombia.
Compatibility: Not stated.
Grade D
Two or more Medium findings, or a High. Only try it in a sandbox.
Not a guarantee. A hygiene check of the source at the commit shown, not a security audit.
INSTALL_REMOTE_SCRIPT SECRETS_PATH_CREDENTIAL
Why this grade
- INSTALL_REMOTE_SCRIPT High
Fetches a script from the network and runs it (a pipe to a shell, or an install hook with a URL).
.agents/skills/cloudflare/references/sandbox/patterns.md, line 40
await sandbox.exec('curl -fsSL https://code-server.dev/install.sh | sh'); - SECRETS_PATH_CREDENTIAL Medium
Mentions a credential store path (~/.ssh, id_rsa, .npmrc, .aws/credentials, credentials.json, .netrc).
.agents/skills/cloudflare/references/tunnel/patterns.md, line 21
- ./credentials.json:/etc/cloudflared/credentials.json:ro
Any High, or two or more Medium findings, give D. One Medium gives C. Low findings or a security Note give B. Each code names a finding behind the letter.
If you think this grade is wrong, email [email protected] with the entry link and your evidence. We aim to acknowledge within two working days and decide within seven. If we confirm an error, we aim to correct it within 24 hours of confirming it. These are aims, not guarantees.
Grades are a hygiene check of the source at the commit shown, on the date checked, not a security audit or a guarantee. The free directory grades are automated. Before release, a PlugVet engineer reviews every paid report and any grade we hold back, including all F grades, against the source code and the evidence we quote.
What was checked
Plain notes from the hygiene checks.
Permissions
Pass
No shell or command execution found, and no extra permission was declared.
Install and update
Serious
install fetches a script from the network.
INSTALL_REMOTE_SCRIPT
.agents/skills/cloudflare/references/sandbox/patterns.md, line 40
await sandbox.exec('curl -fsSL https://code-server.dev/install.sh | sh');
.agents/skills/cloudflare-deploy/references/sandbox/patterns.md, line 40
await sandbox.exec('curl -fsSL https://code-server.dev/install.sh | sh');
Network
Concern
can reach a host that is not written as a fixed address. can reach auth.example.com. The description does not name that host. can reach fake. The description does not name that host. can reach auth-worker.example.com. The description does not name that host. can reach fake-host. The description does not name that host. can reach container. The description does not name that host. can reach imagedelivery.net. The description does not name that host. can reach monitoring.example.com. The descripti
NETWORK_NO_FIXED_HOST NETWORK_UNNAMED_HOST NETWORK_NAMED_HOST
.agents/skills/agents-sdk/references/email.md, line 60
async fetch(request, env) {
.agents/skills/agents-sdk/references/mcp.md, line 138
fetch(request: Request, env: Env, ctx: ExecutionContext) {
.agents/skills/agents-sdk/references/mcp.md, line 143
return MyMCP.serve("/mcp", { binding: "MyMCP" }).fetch(request, env, ctx);
Show more
.agents/skills/agents-sdk/references/mcp.md, line 148
return MyMCP.serveSSE("/sse", { binding: "MyMCP" }).fetch(request, env, ctx);
.agents/skills/agents-sdk/references/queue-retries.md, line 40
const res = await fetch("https://api.example.com/data");
.agents/skills/agents-sdk/references/routing.md, line 32
async fetch(req, env) {
.agents/skills/agents-sdk/references/routing.md, line 36
return agent.fetch(req);
.agents/skills/agents-sdk/references/webhooks-push.md, line 11
async fetch(req: Request, env: Env) {
.agents/skills/agents-sdk/references/webhooks-push.md, line 16
return agent.fetch(req);
.agents/skills/cloudflare/references/ai-gateway/configuration.md, line 10
curl -X POST https://api.cloudflare.com/client/v4/accounts/{account_id}/ai-gateway/gateways \
.agents/skills/cloudflare/references/ai-gateway/configuration.md, line 73
curl https://api.cloudflare.com/client/v4/accounts/{account_id}/ai-gateway/gateways \
.agents/skills/cloudflare/references/ai-gateway/sdk-integration.md, line 100
curl https://gateway.ai.cloudflare.com/v1/{account}/{gateway}/openai/chat/completions \
.agents/skills/cloudflare/references/ai-gateway/troubleshooting.md, line 69
curl -v https://gateway.ai.cloudflare.com/v1/{account}/{gateway}/openai/models \
.agents/skills/cloudflare/references/ai-search/api.md, line 82
curl https://api.cloudflare.com/client/v4/accounts/{ACCOUNT_ID}/autorag/rags/{NAME}/ai-search \
.agents/skills/cloudflare/references/analytics-engine/api.md, line 56
curl -X POST https://api.cloudflare.com/client/v4/accounts/{account_id}/analytics_engine/sql \
.agents/skills/cloudflare/references/api/api.md, line 49
curl "https://api.cloudflare.com/client/v4/zones" \
Secrets
Concern
reads a credential or environment file.
SECRETS_ENV_READ SECRETS_PATH_CREDENTIAL SECRETS_PATH_DOTENV
.agents/skills/cloudflare/references/ai-gateway/README.md, line 40
apiKey: process.env.OPENAI_API_KEY
.agents/skills/cloudflare/references/ai-gateway/README.md, line 69
apiKey: process.env.OPENAI_API_KEY,
.agents/skills/cloudflare/references/tunnel/patterns.md, line 21
- ./credentials.json:/etc/cloudflared/credentials.json:ro
Show more
.agents/skills/cloudflare/references/ai-gateway/configuration.md, line 58
apiKey: process.env.OPENAI_API_KEY,
.agents/skills/cloudflare/references/ai-gateway/configuration.md, line 99
api_key=os.environ.get("OPENAI_API_KEY"),
.agents/skills/cloudflare/references/ai-gateway/sdk-integration.md, line 13
apiKey: process.env.CF_API_TOKEN // Optional for auth gateways
.agents/skills/cloudflare/references/ai-gateway/sdk-integration.md, line 16
const openai = createOpenAI({ apiKey: process.env.OPENAI_API_KEY });
.agents/skills/cloudflare/references/ai-gateway/sdk-integration.md, line 50
apiKey: process.env.OPENAI_API_KEY,
.agents/skills/cloudflare/references/ai-gateway/sdk-integration.md, line 63
apiKey: process.env.ANTHROPIC_API_KEY,
.agents/skills/cloudflare/references/api/configuration.md, line 18
# .env (add to .gitignore)
.agents/skills/cloudflare/references/argo-smart-routing/configuration.md, line 114
# .env
.agents/skills/cloudflare/references/r2-data-catalog/configuration.md, line 172
# .env (never commit)
.agents/skills/cloudflare/references/r2-sql/gotchas.md, line 100
# Or .env file
.agents/skills/cloudflare/references/r2-sql/gotchas.md, line 101
echo "WRANGLER_R2_SQL_AUTH_TOKEN=<your-token>" > .env
.agents/skills/cloudflare/references/turn/configuration.md, line 8
# .env
.agents/skills/cloudflare/references/turnstile/gotchas.md, line 207
# .env
Agent instructions
Pass
No instruction to ignore earlier instructions or to hide a step.
Obfuscation
Note
a file was over the read cap and was not fully read. the file cap was reached before every file was read.
OBFUSCATION_FILE_OVER_READ_CAP OBFUSCATION_FILE_CAP_REACHED
bun.lock, line 1
{
worker-configuration.d.ts, line 1
/* eslint-disable */
.agents/skills/cloudflare-deploy/references/browser-rendering/README.md, line 1
# Cloudflare Browser Rendering Skill Reference
Licence
Pass
A licence file is present (LICENSE).
Maintainer activity
Pass
The latest commit is within the last 365 days.
Note
Hygiene check of commit 3935dd175098. install fetches a script from the network. can reach a host that is not written as a fixed address. can reach auth.example.com. The description does not name that host. can reach fake. The description does not name that host. can reach auth-worker.example.com. The description does not name that host. can reach fake-host. The description does not name that host. can reach container. The description does not name that host. can reach imagedelivery.net. The description does not name that host. can reach monitoring.example.com. The descripti reads a credential or environment file. a file was over the read cap and was not fully read. the file ca
Date and source
Date checked:
github.com
Commit graded: 3935dd17509833e439fd3d892f85f6f587c28899
This link goes to the original host. PlugVet does not host or check what you download from there, and installing it is your own decision and risk.