Skills/PyPI/sops-mcp

sops-mcp@0.12.0

VERIFIED· not started

Publisher claims: "MCP server for creating and managing SOPS-encrypted secrets" Observed in sandbox: no network, touches nothing outside the project, writes no memory.

Registry PyPI (MCP server)Publisher privacyplaybook · publishing for 26 daysInstalls 245Last detonated 14 min ago
$claude mcp add sops-mcp -- uvx sops-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
SOPS_MCP_API_TOKENConfiguration, not credentials: SOPS_MCP_ALLOWED_HOSTS, SOPS_MCP_HOST, SOPS_MCP_LOG_LEVEL, SOPS_MCP_PORT, SOPS_MCP_SOPS_BINARY, SOPS_MCP_TRANSPORT
Where it talks to
no vendor host named in the codeAlso docker.io, ghcr.io, quay.io, cgr.dev — 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 docker.io, ghcr.io, quay.io, cgr.dev as well as its own vendor. The guard injects SOPS_MCP_API_TOKEN only into requests to the host you bind (and its subdomains) and refuses the rest.

$vet-skills run --net declared -- uvx sops-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 2026-11-18 and scored it 85/100 (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
0.1sprocessdependency install exit 1 ·
0.1sclaimednot started: dependency install failed (exit 1); the server itself was not observed
0.1sprocessscript backend runs setup only
0.1sprocessno install scripts to re-run

Static findings

MEDIUM
Python subprocess execution detectedlib/pin_base_images.py:240 · Python subprocess execution detectedroot = subprocess.run(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
Python subprocess execution detectedlib/pin_base_images.py:153 · Python subprocess execution detectedresult = subprocess.run(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
HIGH
Cipher/encoding referenceREADME.md:357 · Cipher/encoding reference — may contain obfuscated instructionsError decrypting tree: Error walking tree: Could not decrypt value: Could not decrypt with AES_GCM: cipher: message authentication failedFix: Put hosts, commands and strings in plain source. Decoding at runtime looks identical to malware and costs points on its own.
AST01
MEDIUM
Python subprocess execution detectedtests/test_domains.py:51 · Python subprocess execution detectedpub = subprocess.run(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
LOW
Dynamic module loadingtests/test_check_trust_store.py:21 · Dynamic module loading (importlib.loader.exec_module via provenance)spec.loader.exec_module(module)Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
Python subprocess execution detectedsrc/sops_mcp/sops.py:357 · Python subprocess execution detectedresult = 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/test_domains.py:43 · 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/test_k8s_secret.py:52 · Python subprocess execution detectedif subprocess.run(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
Python subprocess execution detectedlib/verify_base_images.py:61 · Python subprocess execution detectedsubprocess.run(["cosign", "version"], capture_output=True, check=True)Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
File permission modification commandsrc/sops_mcp/domains.py:154 · File permission modification command — agent changes file ownership/permissionsf"redirect them. Run: chmod go-w {path}"Fix: Request the narrowest permission that works; replace wildcards with the exact paths or hosts.
AST05
MEDIUM
Python subprocess execution detectedtests/test_backward_compat.py:64 · Python subprocess execution detectedpub = 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/test_domain_isolation.py:38 · Python subprocess execution detectedpub = 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/test_domain_isolation.py:25 · Python subprocess execution detectedif 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/test_domain_isolation.py:32 · 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/test_domain_isolation.py:148 · Python subprocess execution detectedresult = 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/test_integration.py:17 · Python subprocess execution detectedif 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/test_server_domains.py:25 · 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/test_backward_compat.py:56 · 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/test_k8s_secret.py:59 · 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
Privileged sudo command.github/workflows/ci.yml:43 · Privileged sudo command — agent may execute with elevated privilegessudo install -m 755 /tmp/age/age /usr/local/bin/ageFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
File permission modification commandsrc/sops_mcp/domains.py:183 · File permission modification command — agent changes file ownership/permissionsf"material. Run: chmod o-r {path}"Fix: Request the narrowest permission that works; replace wildcards with the exact paths or hosts.
AST05
MEDIUM
Python subprocess execution detectedlib/verify_base_images.py:103 · Python subprocess execution detectedroot = 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/test_k8s_secret.py:67 · Python subprocess execution detectedpub = subprocess.run(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
LOW
Dynamic module loadingtests/test_check_trust_store.py:19 · Dynamic module loadingmodule = importlib.util.module_from_spec(spec)Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
Python subprocess execution detectedlib/verify_requirements.py:86 · Python subprocess execution detectedrepo_root = subprocess.run(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
Python subprocess execution detectedsrc/sops_mcp/sops.py:294 · Python subprocess execution detectedresult = subprocess.run(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
Privileged sudo command.github/workflows/ci.yml:44 · Privileged sudo command — agent may execute with elevated privilegessudo install -m 755 /tmp/age/age-keygen /usr/local/bin/age-keygenFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
Python subprocess execution detectedlib/verify_base_images.py:85 · Python subprocess execution detectedresult = 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/test_server_domains.py:31 · Python subprocess execution detectedpub = 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/test_server_domains.py:18 · Python subprocess execution detectedif subprocess.run(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
Privileged sudo command.github/workflows/ci.yml:36 · Privileged sudo command — agent may execute with elevated privilegessudo install -m 755 /tmp/sops /usr/local/bin/sopsFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
Python subprocess execution detectedtests/test_integration.py:28 · Python subprocess execution detectedsubprocess.run(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
Privileged sudo command.github/workflows/publish-mcp-registry.yml:51 · Privileged sudo command — agent may execute with elevated privilegessudo install -m 755 /tmp/mcp-publisher /usr/local/bin/mcp-publisherFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
Python subprocess execution detectedtests/test_k8s_secret.py:107 · 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/test_backward_compat.py:51 · Python subprocess execution detectedif subprocess.run(["which", binary], capture_output=True, check=False).returncode:Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
LOW
HTML comment carrying imperative instructions to the agent.github/ISSUE_TEMPLATE/bug_report.md:14 · HTML comment carrying imperative instructions to the agent · informational: not an instruction fileWhat should it have done instead?Fix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.
AST01
LOW
Authorization escalation languageSECURITY.md:88 · Authorization escalation language · informational: not an instruction file- Compromise of the host running the MCP server itself (e.g. root access,Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
LOW
Instructs the agent to modify its persistent memory or instruction filesdocs/design/domains.md:379 · Instructs the agent to modify its persistent memory or instruction files · informational: not an instruction fileCLAUDE.md (drop the deferred note, add the rule 5 invariant toFix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01

Cost to the agent

Instructions loaded
≈50 tok
1 file · 54 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.