io.github.sailorpepe/undesirables-mcp-server

What we checked

Six static checks, weighted by risk. Every result reflects only what could be observed in the published package and repository — never intent.

• Injection surface

  warn25% of grade

  Tool descriptions/manifest scanned for instruction-injection patterns (imperatives at the model, hidden text, 'ignore previous', data-exfil URLs).

  tool "fantasy_league" description: off-vendor URL in a description (oracle.the-undesirables.com); capability text should not name where data goes. tool "loan_terms_preview" description: off-vendor URL in a description (oracle.the-undesirables.com); capability text should not name where data goes.

• Supply chain

  pass25% of grade

  Package provenance: namespace verification, repo linkage, maintainer count, account age, postinstall scripts, typosquat distance.

  Python build script has no build-time network/exec; repository linkage verified

• Credential hygiene

  pass15% of grade

  How the server takes secrets (env vs plaintext config vs hardcoded); secrets appearing in tool schemas.

  Reads secrets from the environment (e.g. ebay_oracle.py) — the recommended intake shape. PASS = no static red flag; static analysis cannot prove the code honors env-based secret handling at runtime.

• Permission scope

  warn15% of grade

  Declared tools vs. breadth (filesystem, network, exec); flags shell-exec and unbounded filesystem access.

  has both shell/exec and network egress — capable of download-and-run, though no such path was observed (server.py: subprocess.* call; ebay_oracle.py: outbound HTTP/socket call). has both shell/exec and destructive filesystem writes (server.py: subprocess.* call; server.py: destructive filesystem call (shutil.rmtree/os.remove/etc.)). discloses shell/exec capability: server.py: subprocess.* call discloses dynamic code execution: executor.pyi: uses eval(…) discloses dynamic code execution: executor.pyi: uses eval()/exec() discloses broad/destructive filesystem access: server.py: destructive filesystem call (shutil.rmtree/os.remove/etc.) Capability DISCLOSURE, not a verdict: static analysis sees the primitive is present and reachable, not whether its use is attacker-controlled.

• Version behavior

  fail10% of grade

  Diff of tool definitions between versions; new permissions or changed descriptions in a patch release (the postmark-mcp class).

  vs prior 1.1.10 (minor bump): new tool "fantasy_league" whose description contains embedded outbound URL; new tool "loan_terms_preview" whose description contains embedded outbound URL; new tool "oracle_scorecard" appeared; new capability primitive(s) in source: child_process, dynamic-eval, fs-write, http-client, subprocess; new hardcoded outbound host/BCC destination(s): api.ebay.com, dashboard.alchemy.com, dev.pokemontcg.io, developer.ebay.com, github.com, html.duckduckgo.com, the-undesirables.com.

• Transport config

  fail10% of grade

  Remote servers: TLS and auth mode (none/token/OAuth). Local servers: whether the manifest indicates it phones home.

  remote MCP endpoint declares NO authentication (unauthenticated remote — nginx-ui/CVE-2026-33032 class)