Skills/PyPI/recruit-crm-mcp

recruit-crm-mcp@0.19.0

CAUTION· not started

Publisher claims: "MCP server for Recruit CRM" Observed in sandbox: calls astral.sh only, touches nothing outside the project, writes no memory.

Registry PyPI (MCP server)Publisher ebragas · publishing for 263 daysInstalls 172Last detonated 1 h ago
What would fix thisWatchDispute verdict

Coverage

Not started: dependency install failed; the server itself was not observed.
Tested
install scripts, with decoy credentials in place · second launch with the clock 45 days ahead · 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: Caution 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
RECRUIT_CRM_API_KEYRECRUIT_CRM_MCP_SENTRY_DSNSENTRY_DSNConfiguration, not credentials: RCRM_SMOKE_WRITES, RECRUIT_CRM_MCP_ENV, RECRUIT_CRM_MCP_SENTRY_TRACES_RATE
Where it talks to
recruitcrm.io (its own)Also astral.sh, linkedin.com, githubusercontent.com, stoplight.io, python-httpx.org — not the publisher's domain; check what for before connecting.
What the honeypot saw
no credential files read · reached only astral.sh
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 astral.sh, linkedin.com, githubusercontent.com, stoplight.io, python-httpx.org as well as its own vendor. The guard injects RECRUIT_CRM_API_KEY, RECRUIT_CRM_MCP_SENTRY_DSN, SENTRY_DSN only into requests to recruitcrm.io (and its subdomains) and refuses the rest.

$vet-skills run --secrets RECRUIT_CRM_API_KEY=recruitcrm.io,RECRUIT_CRM_MCP_SENTRY_DSN=recruitcrm.io,SENTRY_DSN=recruitcrm.io -- uvx recruit-crm-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 (3 scenarios; not started: dependency install failed; the server itself was not observed) on 2026-11-15 and scored it 62/100 (Caution). It is not known to be malicious, but it has behaviour or code a security policy should decide on before install. Notable findings: Pipe-to-shell pattern; Pipe-to-shell pattern; Direct script execution from GitHub raw URL. Summary: calls astral.sh only, touches nothing outside the project, writes no memory.

Behavior trace

Honeypot run · 1 s · 3 scenarios
t+CategoryObserved action
0.0sprocessinstall script run in the sandbox
0.2snetworkCONNECT tcp://astral.sh:443 · not in the allow-list, refused
0.2sprocessexec /usr/bin/curl
0.2sprocessexited 22: curl: (22) The requested URL returned error: 403
0.3sprocessdependency install exit 1 ·
0.3sclaimednot started: dependency install failed (exit 1); the server itself was not observed
0.3sprocessscript backend runs setup only
0.4sprocesssecond launch, clock +45 days, CI unset
0.4snetworkCONNECT tcp://astral.sh:443 · not in the allow-list, refused
0.4sprocessexec /usr/bin/curl
0.4sprocessexited 22: curl: (22) The requested URL returned error: 403

Static findings

LOW
Instructs the agent to modify its persistent memory or instruction filesCHANGELOG.md:750 · Instructs the agent to modify its persistent memory or instruction files · informational: not an instruction fileand rejection guard tests for sort params. Update CLAUDE.md with API gotchas and TDD workflow forFix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
CRITICAL
Pipe-to-shell patterninstall.sh:22 · Pipe-to-shell pattern — downloads and immediately executes remote codecurl -LsSf https://astral.sh/uv/install.sh | shFix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST06
CRITICAL
Pipe-to-shell patternsrc/recruit_crm_mcp/install.py:88 · Pipe-to-shell pattern — downloads and immediately executes remote codeprint(" curl -LsSf https://astral.sh/uv/install.sh | sh")Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST06
MEDIUM
Remote installer piped to shellinstall.sh:3 · Remote installer piped to shell# Usage: curl -LsSf https://raw.githubusercontent.com/ebragas/recruitcrm-mcp/main/install.sh | bashFix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST07
MEDIUM
Remote installer piped to shellsrc/recruit_crm_mcp/install.py:109 · Remote installer piped to shell["sh", "-c", "curl -LsSf https://astral.sh/uv/install.sh | sh"],Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST07
HIGH
Direct script execution from GitHub raw URLinstall.sh:3 · Direct script execution from GitHub raw URL — unverified code source# Usage: curl -LsSf https://raw.githubusercontent.com/ebragas/recruitcrm-mcp/main/install.sh | bashFix: Pin versions and sources; vendor anything fetched at install time.
AST06
MEDIUM
Access to sensitive file pathstests/integration/test_api.py:3 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system filesRequires RECRUIT_CRM_API_KEY in environment (loaded from .env via pytest-dotenv).Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
MEDIUM
Python subprocess execution detectedsrc/recruit_crm_mcp/install.py:113 · Python subprocess execution detectedsubprocess.run(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
Remote installer piped to shellsrc/recruit_crm_mcp/install.py:88 · Remote installer piped to shellprint(" curl -LsSf https://astral.sh/uv/install.sh | sh")Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST07
HIGH
Collapsed <details> block carrying instructionsREADME.md:29 · Collapsed <details> block carrying instructions<summary>Want to review the script first?</summary> **macOS / Linux:** ```bash curl -LsSf https://raw.githubusercontent.com/ebragas/recruitcrm-mcp/main/install.Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
CRITICAL
Pipe-to-shell patterninstall.sh:3 · Pipe-to-shell pattern — downloads and immediately executes remote code# Usage: curl -LsSf https://raw.githubusercontent.com/ebragas/recruitcrm-mcp/main/install.sh | bashFix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST06
LOW
Instructs the agent to modify its persistent memory or instruction filesCHANGELOG.md:860 · Instructs the agent to modify its persistent memory or instruction files · informational: not an instruction file- Update CLAUDE.md to reflect eager client init patternFix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
CRITICAL
Pipe-to-shell patternsrc/recruit_crm_mcp/install.py:109 · Pipe-to-shell pattern — downloads and immediately executes remote code["sh", "-c", "curl -LsSf https://astral.sh/uv/install.sh | sh"],Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST06
MEDIUM
Remote installer piped to shellinstall.sh:22 · Remote installer piped to shellcurl -LsSf https://astral.sh/uv/install.sh | shFix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST07
LOW
Instructs the agent to modify its persistent memory or instruction filesCHANGELOG.md:491 · Instructs the agent to modify its persistent memory or instruction files · informational: not an instruction fileAdd Copilot review request step to the workflow in CLAUDE.md and ensure the review-pr-comments skillFix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
MEDIUM
Python subprocess execution detectedsrc/recruit_crm_mcp/install.py:108 · Python subprocess execution detectedsubprocess.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
≈4,125 tok
2 files · 81 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

No advisories in OSV for recruit-crm-mcp@0.19.0 as of 45 min ago. This is the package itself, not its dependencies.

What would make this Verified

18 points to 80 · weights: behavior 45%, static 25%, prompt 15%, publisher 15%
  1. Pipe-to-shell pattern≈ +9 on the totalBuild commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
  2. Unclaimed publisher≈ +8 on the totalClaim ebragas: a verified publisher gets +50 on publisher trust. It is free and usually instant with GitHub sign-in.
  3. Hidden instructions≈ +6 on the totalRemove HTML comments, zero-width characters and white-on-white text that carry instructions. Everything the agent is meant to read should be visible to the person reading the file.
  4. Direct script execution from GitHub raw URL≈ +4 on the totalPin versions and sources; vendor anything fetched at install time.
  5. Remote installer piped to shell≈ +2 on the totalBuild commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
  6. Access to sensitive file paths≈ +2 on the totalStop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
Publish a new version to PyPI, then queue it here. Not your skill? Claim the handle to get verdict changes by email.Claim ebragasPropose a patch to the maintainer