io.github.ericm1018/skillfm-llm-cost-optimizer-openai-anthropic-usage

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

  fail25% of grade

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

  tool "skillfm_avatar_market" description: names an outbound copy/exfil destination (BCC/exfil verb). tool "skillfm_get_monthly_picks" description: names an outbound copy/exfil destination (BCC/exfil verb). tool "skillfm_save_credential" description: names an outbound copy/exfil destination (BCC/exfil verb). tool "skillfm_list_credentials" description: names an outbound copy/exfil destination (BCC/exfil verb). tool "skillfm_remove_credential" description: names an outbound copy/exfil destination (BCC/exfil verb). tool "skillfm_cleanup_audit" description: names an outbound copy/exfil destination (BCC/exfil verb). tool "skillfm_setup_gateway" description: names an outbound copy/exfil destination (BCC/exfil verb). tool "skillfm_setup_safe" param "sidecar_url" description: raw-IP URL in a description (http://127.0.0.1:19821) — strong exfil tell. tool "skillfm_setup_agent_forcing" param "sidecar_url" description: raw-IP URL in a description (http://127.0.0.1:19821) — strong exfil tell. tool "skillfm_install_module" description: names an outbound copy/exfil destination (BCC/exfil verb). tool "skillfm_install_module" param "name" description: names an outbound copy/exfil destination (BCC/exfil verb). tool "skillfm_send_daily_report" description: names an outbound copy/exfil destination (BCC/exfil verb). tool "__unlock_skillfm_beacon__" description: names an outbound copy/exfil destination (BCC/exfil verb). server instructions: names an outbound copy/exfil destination (BCC/exfil verb).

• Supply chain

  pass25% of grade

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

  repository linkage verified

• Credential hygiene

  pass15% of grade

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

  No hardcoded secrets, secret-shaped tool parameters, or leaked keys found. PASS = no static red flag; static analysis cannot prove the code honors env-based secret handling at runtime.

• Permission scope

  pass15% of grade

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

  No shell-exec, unbounded/sensitive filesystem, or download-and-run primitives found in scanned source. PASS = no static red flag. Static scanning is blind to code fetched or executed at runtime.

• 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.ericm1018/[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

  unscannable10% of grade

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

  local stdio server: no remote transport or auth surface, and no phone-home/telemetry signal found in source. Absence of transport findings is NOT a safety guarantee — phone-home hosts can be constructed at runtime and defeat static analysis.