Skills/PyPI/mcp-codebase-searcher

mcp-codebase-searcher@0.2.14

VERIFIED· install only

Publisher claims: "A Python tool to scan codebases, search for text/regex patterns, and elaborate on findings using AI models via LiteLLM." Observed in sandbox: no network, touches nothing outside the project, writes no memory.

Registry PyPI (MCP server)Publisher sakilmostak · publishing for 537 daysInstalls 73Last detonated 7d ago
$claude mcp add mcp-codebase-searcher -- uvx mcp-codebase-searcher
WatchReport an issue

Coverage

Nothing executable in the bundle ran; the trace covers the install step only.
Tested
every file read, file written and host contacted by what ran
Not tested
use of the skill by an agent

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

Code inventory arrives with this version's next honeypot run.
It will ask for
unknown until the next run
Where it talks to
unknown until the next run
What the honeypot saw
no credential files read · no network
What we could not test
use of the skill by an agent

Not enough was observed to say yet. Nothing executable in the bundle ran; the trace covers the install step only. This version's code has not been inventoried for credentials and hosts either; both arrive with its next honeypot run (popular servers first). `vet-skills try mcp-codebase-searcher` runs it now and prints the full answer.

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 (1 scenario; nothing executable in the bundle ran; the trace covers the install step only) on 2026-11-07 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 · 1 scenarios · 0 deviations
t+CategoryObserved action
0.0sprocessno install scripts in bundle
0.0sprocessscript backend runs setup only
0.0sprocessscript backend runs setup only
0.0sprocessno install scripts to re-run

Static findings

HIGH
Access to sensitive file pathssrc/mcp_searcher.py:8 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system filesfrom dotenv import load_dotenv # Added for explicit .env loadingFix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
HIGH
Access to sensitive file pathssrc/config.py:8 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system filesLoads the Google API key, trying .env first, then environment variables.Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
HIGH
Access to sensitive file pathssrc/config.py:10 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system filesPrints a warning if .env is used but the key isn't in it or if not found at all.Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
HIGH
Access to sensitive file pathssrc/config.py:14 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system files# print(f"DEBUG: [config.py] Expected .env path: {dotenv_path}", file=sys.stderr)Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
HIGH
Access to sensitive file pathssrc/config.py:12 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system filesdotenv_path = os.path.join(os.getcwd(), '.env')Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
HIGH
Access to sensitive file pathssrc/config.py:20 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system files# print(f"DEBUG: [config.py] .env file found at {dotenv_path}", file=sys.stderr)Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
HIGH
Access to sensitive file pathssrc/mcp_searcher.py:311 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system files# This explicitly loads .env here, overriding any system env var if key is present in .envFix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
HIGH
Access to sensitive file pathssrc/mcp_searcher.py:310 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system files# Load .env from current working directory to check for GOOGLE_API_KEYFix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
HIGH
Access to sensitive file pathssrc/mcp_searcher.py:313 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system files# but this ensures CLI-level .env takes precedence if no direct arg or config file key.Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
HIGH
Access to sensitive file pathssrc/mcp_server.py:39 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system files"""Ensure we try to load .env variables locally for litellm settings."""Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
MEDIUM
File type combined with upload actiontests/test_output_generator.py:90 · File type combined with upload action — agent may exfiltrate local data filesself.assertIn("Match in: file1.txt", output)Fix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.
AST07
LOW
Rule modification attemptREADME.md:76 · Rule modification attempt — overwriting existing instructions · informational: not an instruction file · informational: not an instruction file · informational: not an instruction file**Rule 2: The LLM should be instructed to use absolute paths.**Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
HIGH
Access to sensitive file pathssrc/mcp_server.py:40 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system filesdotenv_path = os.path.join(os.getcwd(), '.env')Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
MEDIUM
File type combined with upload actiontests/test_output_generator.py:80 · File type combined with upload action — agent may exfiltrate local data filesself.assertIn("Match in: file1.txt", output)Fix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.
AST07
MEDIUM
File type combined with upload actiontests/test_output_generator.py:126 · File type combined with upload action — agent may exfiltrate local data filesself.assertIn("## File: `file1.txt`", output)Fix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.
AST07
LOW
Rule modification attemptREADME.md:73 · Rule modification attempt — overwriting existing instructions · informational: not an instruction file · informational: not an instruction file · informational: not an instruction file**Rule 1: Always use FULL absolute paths for your executable command.**Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
MEDIUM
File type combined with upload actiontests/test_output_generator.py:136 · File type combined with upload action — agent may exfiltrate local data filesself.assertIn("## File: `file1.txt`", output)Fix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.
AST07

Cost to the agent

Instructions loaded
≈71 tok
1 file · 28 in bundle

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 mcp-codebase-searcher@0.2.14 as of 2 h ago. This is the package itself, not its dependencies.