Awslabs Git Repo Research MCP Server
awslabs-git-repo-research-mcp-server
PyPI
v1.0.15
Published by awslabs — no publish provenance and no vendor-owned scope, so the publisher could not be verified. The repository link below is self-declared.
Every server starts at 100. These are the exact deductions the deterministic engine applied — each one reproducible, none of it an opinion or an LLM's guess:
| Points | What was found | Category |
|---|---|---|
| −15.4 | Obfuscated / encoded payload in server code MTC-SRC-004 | injection |
Capability observations and info notes are shown under Findings but never scored.
Open any row's finding below for the file, line and evidence behind the deduction.
Findings 5
high Reads a sensitive credential path or dumps the environment (tests/test_server.py)MTC-SRC-006
In the server's implementation (`tests/test_server.py:546`): Reading private keys / cloud credentials, or serializing the whole environment, is a sensitive-data source that becomes exfiltration when combined with any egress. This is read from the code itself — not from the tool description — so a poisoned server cannot hide it behind honest-looking metadata.
Evidence: .aws/credentials
Fix: Review this call path: confirm it never receives unsanitized tool input, constrain it, or remove it. Treat a server whose code reaches these sinks as high-capability regardless of what its tools claim.
Location: server tests/test_server.py
high Obfuscated / encoded payload in server code (tests/test_server.py)MTC-SRC-004
In the server's implementation (`tests/test_server.py:195`): Decoding an encoded blob and executing it is how malicious logic is hidden from human review of the source. This is read from the code itself — not from the tool description — so a poisoned server cannot hide it behind honest-looking metadata.
Evidence: \x00\x00\x00\x01\x00\x00\x00\x01\x08\x06\x00\x00\x00\x1f\x15\xc4\x89\x00\x00\x00
Fix: Review this call path: confirm it never receives unsanitized tool input, constrain it, or remove it. Treat a server whose code reaches these sinks as high-capability regardless of what its tools claim.
Location: server tests/test_server.py
high Shell/command execution in server code (tests/test_local_repository.py)MTC-SRC-002
In the server's implementation (`tests/test_local_repository.py:64`): Spawning a shell/process is command-execution capability; with unsanitized tool input it is command injection / RCE. This is read from the code itself — not from the tool description — so a poisoned server cannot hide it behind honest-looking metadata.
Evidence: subprocess.run(
Fix: Review this call path: confirm it never receives unsanitized tool input, constrain it, or remove it. Treat a server whose code reaches these sinks as high-capability regardless of what its tools claim.
Location: server tests/test_local_repository.py
high Shell/command execution in server code (tests/test_server.py)MTC-SRC-002
In the server's implementation (`tests/test_server.py:97`): Spawning a shell/process is command-execution capability; with unsanitized tool input it is command injection / RCE. This is read from the code itself — not from the tool description — so a poisoned server cannot hide it behind honest-looking metadata.
Evidence: subprocess.run(
Fix: Review this call path: confirm it never receives unsanitized tool input, constrain it, or remove it. Treat a server whose code reaches these sinks as high-capability regardless of what its tools claim.
Location: server tests/test_server.py
medium Hardcoded egress to an external endpoint (awslabs/git_repo_research_mcp_server/github_search.py)MTC-SRC-003
In the server's implementation (`awslabs/git_repo_research_mcp_server/github_search.py:101`): A hardcoded outbound call to a fixed external host inside server code is a classic exfiltration/telemetry channel — especially paired with reads of local data. This is read from the code itself — not from the tool description — so a poisoned server cannot hide it behind honest-looking metadata.
Evidence: requests.post(
'https://api.github.com/graphql'
Fix: Review this call path: confirm it never receives unsanitized tool input, constrain it, or remove it. Treat a server whose code reaches these sinks as high-capability regardless of what its tools claim.
Location: server awslabs/git_repo_research_mcp_server/github_search.py
What this scan could not see
- No tools were enumerated, so prompt-injection, capability and toxic-flow analysis had no tool surface to inspect. To grade a package’s real runtime tools, scan the running server: --command "npx -y <package>".
Versions
Scan history per published version. The engine is deterministic — the same version always yields the same score, so a changed score means the package itself changed.
| Version | Score | Findings | Engine | Scanned |
|---|---|---|---|---|
v1.0.15 latest |
B 85/100 | 5 | 1.5.0 | 2026-07-22 |
Embed this score
Show this server's live Trust Score in your README, docs or website. The badge is served straight from the registry and updates automatically after every rescan — no API key needed. It links back to this page, so anyone who sees the grade can also read the findings behind it instead of taking a number on faith.
Verify this score yourself
The score above is reproducible: the same package version always yields the same result. Run it locally or over the free API — no account, no LLM, fully deterministic.
npx mcptrustchecker scan awslabs-git-repo-research-mcp-server --online --registry pypiMore in Cloud & DevOps
Security scan results for the Actual MCP server.
Security scan results for the Adguard MCP server.
Security scan results for the Admob MCP server.
Security scan results for the Aem MCP server.
Security scan results for the Agent Domains MCP server.
Security scan results for the Agent Infra MCP server.