Skills/PyPI/quotable-mcp

quotable-mcp@0.2.0

VERIFIED· not started

Publisher claims: "Local-first MCP server and CLI that turns recordings, podcast feeds and media URLs into cite-ready transcripts" Observed in sandbox: no network, touches nothing outside the project, writes no memory.

Registry PyPI (MCP server)Publisher rfung4 · publishing for 26 daysInstalls 297Last detonated 14 min ago
$claude mcp add quotable-mcp -- uvx quotable-mcp
WatchReport an issue

Coverage

Not started: dependency install failed; the server itself was not observed.
Tested
the dependency install step · every file read, file written and host contacted by what ran
Not tested
server startup · the tool list · tool behavior

What this means for the label: Verified here covers what ran. The server's tools were not exercised with a real credential, so nothing about their behavior is asserted; the credential summary below says what to do with that.

Before you give it your token

It will ask for
HF_TOKENOPENAI_API_KEYQUOTABLE_HF_TOKENConfiguration, not credentials: QUOTABLE_DAEMON, QUOTABLE_MODEL_TTL
Where it talks to
no vendor host named in the codeAlso deno.com, youtu.be, huggingface.co — not the publisher's domain; check what for before connecting.
What the honeypot saw
no credential files read · no network
What we could not test
server startup · the tool list · tool behavior

Connect it with a scoped credential, under the guard, and read the third-party hosts first. The code names deno.com, youtu.be, huggingface.co as well as its own vendor. The guard injects HF_TOKEN, OPENAI_API_KEY, QUOTABLE_HF_TOKEN only into requests to the host you bind (and its subdomains) and refuses the rest.

$vet-skills run --net declared -- uvx quotable-mcp

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 ran it in the KillerSkills honeypot sandbox (2 scenarios; not started: dependency install failed; the server itself was not observed) on 2026-11-15 and scored it 81/100 (Verified). In what ran, nothing we could detect went wrong: no undeclared network egress, no credential reads, no persistent instruction writes. What it does with a real credential was not observed; the static findings and the publisher carry the rest of the score. Summary: no network, touches nothing outside the project, writes no memory.

Behavior trace

Honeypot run · 0 s · 2 scenarios · 0 deviations
t+CategoryObserved action
0.0sprocessno install scripts in bundle
0.2sprocessdependency install exit 1 ·
0.2sclaimednot started: dependency install failed (exit 1); the server itself was not observed
0.2sprocessscript backend runs setup only
0.2sprocessno install scripts to re-run

Static findings

MEDIUM
Python subprocess execution detectedevals/mcp_probe.py:44 · Python subprocess execution detectedversion = subprocess.run(Fix: Put hosts, commands and strings in plain source. Decoding at runtime looks identical to malware and costs points on its own.
AST05
MEDIUM
Python subprocess execution detectedevals/build_corpus.py:108 · Python subprocess execution detecteddone = subprocess.run(cmd, stdin=subprocess.DEVNULL, capture_output=True, text=True)Fix: Put hosts, commands and strings in plain source. Decoding at runtime looks identical to malware and costs points on its own.
AST05
MEDIUM
Python subprocess execution detectedevals/report.py:684 · Python subprocess execution detectedout = subprocess.run(Fix: Put hosts, commands and strings in plain source. Decoding at runtime looks identical to malware and costs points on its own.
AST05
MEDIUM
Python subprocess execution detectedtests/unit/stdio_probe.py:20 · Python subprocess execution detectedsubprocess.run(["sh", "-c", "echo leak"], timeout=5)Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
Python subprocess execution detectedtests/unit/test_daemon.py:133 · Python subprocess execution detectedsubprocess.run(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
Python subprocess execution detectedtests/integration/test_shared_process.py:67 · Python subprocess execution detectedstate = subprocess.run(["ps", "-o", "stat=", "-p", str(pid)], capture_output=True, text=True)Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
Python subprocess execution detectedsrc/quotable/shim.py:191 · Python subprocess execution detectedreturn subprocess.Popen(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
Python subprocess execution detectedtests/conftest.py:26 · Python subprocess execution detectedargs = subprocess.run(["ps", "-o", "args=", "-p", str(pid)], capture_output=True, text=True)Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
Python subprocess execution detectedevals/run.py:390 · Python subprocess execution detectedproc = subprocess.Popen(Fix: Put hosts, commands and strings in plain source. Decoding at runtime looks identical to malware and costs points on its own.
AST05
MEDIUM
Python subprocess execution detectedevals/mcp_probe.py:43 · Python subprocess execution detectedsubprocess.run(["uv", "build"], cwd=ROOT, check=True, stdin=subprocess.DEVNULL)Fix: Put hosts, commands and strings in plain source. Decoding at runtime looks identical to malware and costs points on its own.
AST05
MEDIUM
Python subprocess execution detectedtests/integration/test_shared_process.py:310 · Python subprocess execution detectedproc = subprocess.Popen(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
Access to sensitive file pathstests/unit/test_feeds.py:75 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system files@pytest.mark.parametrize("url", ["file:///etc/passwd", "ftp://media.example/a.srt", "data:,x"])Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
MEDIUM
Python subprocess execution detectedtests/unit/test_daemon.py:139 · Python subprocess execution detectedproc = subprocess.run(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
Python subprocess execution detectedtests/unit/test_daemon.py:460 · Python subprocess execution detectedproc = subprocess.run(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
Python subprocess execution detectedtests/unit/stdio_probe.py:18 · Python subprocess execution detectedcat = subprocess.run(["cat"], capture_output=True, timeout=5)Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
HIGH
Latin word with Cyrillic or Greek look-alike letters (homoglyph)evals/README.md:130 · Latin word with Cyrillic or Greek look-alike letters (homoglyph)ΔstartFix: Put hosts, commands and strings in plain source. Decoding at runtime looks identical to malware and costs points on its own.
AST01
MEDIUM
Access to sensitive file pathstests/unit/test_audio.py:196 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system filesassert not audio.is_url("file:///etc/passwd")Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
MEDIUM
Access to sensitive file pathstests/unit/test_captions.py:230 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system filesinfo = {"subtitles": {"en": [{"ext": "vtt", "url": "file:///etc/passwd"}]}}Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
MEDIUM
Python subprocess execution detectedevals/report.py:108 · Python subprocess execution detecteddone = subprocess.run(Fix: Put hosts, commands and strings in plain source. Decoding at runtime looks identical to malware and costs points on its own.
AST05
MEDIUM
MCP server using network transport (SSE/HTTP)src/quotable/server.py:5 · MCP server using network transport (SSE/HTTP) — data sent over networkstdio isolation is the SDK's: ``run()`` calls ``MCPServer.run("stdio")`` and never passesFix: Namespace tool names and keep tool descriptions literal; no instructions to the agent inside them.
AST04
HIGH
Hidden zero-width characters detectedsrc/quotable/feeds.py:480 · Hidden zero-width characters detected — may conceal contentfor block in re.split(r"(?:\r?\n){2,}", body.replace("", "").strip()):Fix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.
AST07
MEDIUM
Python subprocess execution detectedtests/unit/test_cli.py:186 · Python subprocess execution detectedout = subprocess.run(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
Python subprocess execution detectedtests/unit/test_daemon.py:456 · Python subprocess execution detected"subprocess.run(['sh', '-c', 'echo from-child; cat; pwd']); "Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
Python subprocess execution detectedevals/scenarios.py:105 · Python subprocess execution detectedout = subprocess.run(Fix: Put hosts, commands and strings in plain source. Decoding at runtime looks identical to malware and costs points on its own.
AST05
MEDIUM
Python subprocess execution detectedevals/run.py:209 · Python subprocess execution detectedout = subprocess.run(Fix: Put hosts, commands and strings in plain source. Decoding at runtime looks identical to malware and costs points on its own.
AST05
MEDIUM
Python subprocess execution detectedevals/shared_process_check.py:77 · Python subprocess execution detectedstate = subprocess.run(["ps", "-o", "stat=", "-p", str(pid)], capture_output=True, text=True)Fix: Put hosts, commands and strings in plain source. Decoding at runtime looks identical to malware and costs points on its own.
AST05
MEDIUM
Python subprocess execution detectedtests/unit/test_daemon.py:471 · Python subprocess execution detectedproc = subprocess.run(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
Python subprocess execution detectedevals/shared_process_check.py:47 · Python subprocess execution detectedout = subprocess.run(Fix: Put hosts, commands and strings in plain source. Decoding at runtime looks identical to malware and costs points on its own.
AST05
MEDIUM
File permission modification commandsrc/quotable/shim.py:144 · File permission modification command — agent changes file ownership/permissionsfix=f"chmod 700 {path}",Fix: Request the narrowest permission that works; replace wildcards with the exact paths or hosts.
AST05
HIGH
Latin word with Cyrillic or Greek look-alike letters (homoglyph)evals/README.md:129 · Latin word with Cyrillic or Greek look-alike letters (homoglyph)ΔstartFix: Put hosts, commands and strings in plain source. Decoding at runtime looks identical to malware and costs points on its own.
AST01
MEDIUM
Access to sensitive file pathstests/unit/test_feeds.py:142 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system files"location", ["file:///etc/passwd", "ftp://127.0.0.1/a.srt", "data:text/plain,hi"]Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
MEDIUM
Access to sensitive file pathstests/unit/test_pipeline.py:238 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system files@pytest.mark.parametrize("source", ["/no/such/file.mp3", "ftp://host/a.mp3", "file:///etc/passwd"])Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
MEDIUM
Access to sensitive file pathstests/unit/test_store.py:65 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system files"/etc/passwd",Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
MEDIUM
Python subprocess execution detectedtests/unit/test_shim.py:133 · Python subprocess execution detectedout = subprocess.run([sys.executable, "-c", probe], capture_output=True, text=True, check=True)Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
Access to sensitive file pathstests/unit/test_feeds.py:94 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system files{url: b"1\n00:00:00,000 --> 00:00:01,000\nx\n"}, {url: "file:///etc/passwd"}Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
MEDIUM
File permission modification commandtests/unit/test_shim.py:181 · File permission modification command — agent changes file ownership/permissionsassert "chmod 700" in err.value.fixFix: Request the narrowest permission that works; replace wildcards with the exact paths or hosts.
AST05
MEDIUM
Access to sensitive file pathstests/unit/test_feeds.py:453 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system files@pytest.mark.parametrize("url", ["javascript:alert(1)", "file:///etc/passwd", "/relative.mp3"])Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
MEDIUM
Python subprocess execution detectedtests/unit/test_shim.py:215 · Python subprocess execution detectedout = subprocess.run(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05

Cost to the agent

Instructions loaded
≈638 tok
2 files · 73 in bundle
Tool list per prompt
≈0 tok
0 tools · 0 per tool
Handshake
no reply
launch to tools/list, stdio
Undocumented tools
0
description under 20 chars · avg 0

Tokens estimated at four characters each. The tool list is re-read by the agent on every turn, so it is the number to compare between servers that do the same job: ranked across the index.

Known vulnerabilities

Not checked against OSV yet; the weekly check has not reached this version.