selph-mcp@1.5.0
CAUTION· static onlyPublisher claims: "Selph MCP CLI — Claude Code onboarding helper for the Selph Remote MCP." Observed in sandbox: static analysis only — behavior not yet observed.
Coverage
Static only; nothing was run yet.The label rests on the code, the instruction files and the publisher. The honeypot run replaces this verdict when it completes.
Before you give it your token
- It will ask for
SELPH_API_KEYSELPH_BEARER_TOKENor--persist-api-key/--bearer-tokenConfiguration, not credentials: CHECKPOINT_POOL_MAX, CHROMA_CLEAR_AT_BOOT, CHROMA_HOST, CHROMA_PATH, CHROMA_PORT, MCP_HOST, MCP_PORT, SELPH_API_URL, SELPH_CLIENT_TIMEOUT, SELPH_CONSUMER_ID, SELPH_GET_FINGERPRINT_AVAILABLE, SELPH_KG_DB_POOL_MAX, SELPH_MCP_EXTRACTION_CONCURRENCY, SELPH_MCP_SSE_HOST, SELPH_MCP_SSE_PORT, SELPH_MCP_TRANSPORT, SELPH_OBSERVE_SYNC_BUDGET_MS, SELPH_OBSERVE_SYNC_BUDGET_SECS, SELPH_USER_ID- Where it talks to
- selph.ai (its own)Also azurecontainerapps.io — not the publisher's domain; check what for before connecting.
- What the honeypot saw
- nothing has run yet
- What we could not test
- everything: the server has not run yet
Run it before you trust it. Nothing has run yet: the code was read, the server was not. `vet-skills try` runs this exact version in the honeypot in about a minute.
Never paste a credential into a chat, a ticket or a report, including ours. How the guard holds it.
Is [email protected] safe to install?
KillerSkills analysed it statically (a sandbox run is pending) on 2026-11-18 and scored it 61/100 (Caution). It is not known to be malicious, but it has behaviour or code a security policy should decide on before install. Notable findings: Sends the whole process environment out. Summary: static analysis only — behavior not yet observed.
Behavior trace
Queued for honeypot run · static analysis onlyThis version has not been detonated yet. The score above counts behavior as unknown (50/100), so it cannot read Verified until the honeypot run completes and replaces this verdict.
Static findings
_spec.loader.exec_module(_old_server_module)Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.# chmod BEFORE replace so the public path never briefly exists atFix: Request the narrowest permission that works; replace wildcards with the exact paths or hosts."""Argument > env > default."""Fix: Never read or enumerate credential locations; accept a documented environment variable instead."""Atomically write ``payload`` as JSON, chmod 0o600.Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.``%USERPROFILE%\\.config\\selph-mcp\\credentials.json`` — chmod has noFix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose."failed to chmod cache dir to 0700",Fix: Request the narrowest permission that works; replace wildcards with the exact paths or hosts.# AND the ensure_cache_dir mkdir/chmod outside the workspace, even whenFix: Request the narrowest permission that works; replace wildcards with the exact paths or hosts.- ``credentials.json`` — credentials (separate; chmod 0600; never logged)Fix: Request the narrowest permission that works; replace wildcards with the exact paths or hosts.:func:`save_credentials` — write+chmod 0o600, atomic.Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.proc = subprocess.run(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.refusal the chmod 0o700 / 0o600 protections do not apply to theFix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.token. On Windows the chmod is a no-op (NTFS ACLs apply instead) — thatFix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose._old_server_module = _importlib_util.module_from_spec(_spec)Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.print("The bearer_token has been written to that file (chmod 0600).")Fix: Request the narrowest permission that works; replace wildcards with the exact paths or hosts.help="Append the Selph CLAUDE.md block (idempotent).")Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.Cost to the agent
Tokens estimated at four characters each. Skills load their instruction text when triggered; the figure is what that costs.
Known vulnerabilities
No advisories in OSV for selph-mcp@1.5.0 as of 7 min ago. This is the package itself, not its dependencies.
What would make this Verified
19 points to 80 · weights: behavior 45%, static 25%, prompt 15%, publisher 15%- Unclaimed publisher≈ +8 on the totalClaim selph-engineer: a verified publisher gets +50 on publisher trust. It is free and usually instant with GitHub sign-in.
- Sends the whole process environment out≈ +4 on the totalNever read or enumerate credential locations; accept a documented environment variable instead.
- File permission modification command≈ +2 on the totalRequest the narrowest permission that works; replace wildcards with the exact paths or hosts.
- Python subprocess execution detected≈ +2 on the totalBuild commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
- Dynamic module loading≈ +1 on the totalBuild commands from fixed arguments; do not interpolate untrusted strings into a shell.