io.github.hassanahashish-design/agent-signals-mcp

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

  unscannable25% of grade

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

  No tool descriptions, server instructions, prompts, or resources were fetched; nothing to scan for injection.

• Supply chain

  pass25% of grade

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

  repository linkage verified

• Credential hygiene

  unscannable15% of grade

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

  No source files, package manifest, or tool schemas were fetched; cannot assess credential handling.

• Permission scope

  unscannable15% of grade

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

  No source files, package.json, or pyproject were fetched; cannot infer capability scope.

• Version behavior

  unscannable10% of grade

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

  no prior version to diff (first sight of io.github.hassanahashish-design/[email protected]); version-drift / rug-pull cannot be evaluated. Cold-start risk is covered by point-in-time checks (injection_surface, supply_chain, credential_hygiene), not here.

• Transport config

  pass10% of grade

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

  remote endpoint "https://mcp.apify.com/?actors=oblanceolate_mandola/company-hiring-signals,oblanceolate_mandola/sec-edgar-filings,oblanceolate_mandola/research-paper-search,oblanceolate_mandola/github-repo-search,oblanceolate_mandola/hacker-news-monitor" uses TLS (https); remote endpoint "https://mcp.apify.com/?actors=oblanceolate_mandola%2Fcompany-hiring-signals%2Coblanceolate_mandola%2Fsec-edgar-filings%2Coblanceolate_mandola%2Fresearch-paper-search%2Coblanceolate_mandola%2Fgithub-repo-search%2Coblanceolate_mandola%2Fhacker-news-monitor%2Coblanceolate_mandola%2Ffederal-register-monitor%2Coblanceolate_mandola%2Fclinical-trials-search%2Coblanceolate_mandola%2Fstackoverflow-search%2Coblanceolate_mandola%2Fgdelt-news-monitor%2Coblanceolate_mandola%2Fcourt-opinions-search" uses TLS (https); remote endpoint uses OAuth (strongest auth mode)