memsearch
Not malicious, needs a look Reviewed: expected behaviour
Bawwab's static rules found patterns that deserve a human look. This is not a finding that the package is malicious; the review notes below say what each pattern turned out to be.
Why it was flagged
The static rules marked this “Not malicious, needs a look” because of:
remote-code.pipe-shell: Pipes a download into a shell (high, 1× · first at hooks/session-start.sh:26)
- Kind
- Plugin
- Source
- github
- Repository
- zilliztech/memsearch / plugins/claude-code
- Commit
ff6bdc329fa12875e9770a301cd57dabe7d614d3- Listed in
- zilliztech/memsearch
- Popularity
- 2,913 GitHub stars (2026-11-20)
- Link
- https://github.com/zilliztech/memsearch/tree/ff6bdc329fa12875e9770a301cd57dabe7d614d3/plugins/claude-code
- Scanned
- 2026-11-20T23:19:27+00:00
- Scan time
- 1.9 s
- Scanned as
- plugin
Review note: No malicious code found; one risky habit: its session-start hook silently pipes Astral's official uv installer to a shell when uvx is missing.
Findings (1)
remote-code.pipe-shell: Pipes a download into a shell high
hooks/session-start.sh:26
OWASP LLM LLM03 Supply ChainOWASP Agentic ASI04 Agentic Supply Chain VulnerabilitiesOWASP Agentic ASI05 Unexpected Code Execution (RCE)MITRE ATLAS AML.T0050 Command and Scripting InterpreterCWE CWE-494 Download of Code Without Integrity Check
curl -LsSf https://astral.sh/uv/install.sh | sh 2>/dev/null
What this means: Executes whatever the remote server returns, unreviewed.
The rule's general advice: Download, verify a checksum, then run. (see the review note for this case)
Expected for what this tool does
Not malicious, but risky: when uvx is missing, the SessionStart hook pipes a remote script to a shell without asking and hides its output ('curl -LsSf https://astral.sh/uv/install.sh | sh 2>/dev/null'), installing uv into ~/.local/bin. The script is Astral's official uv installer, so this is an install habit rather than an attack, but it runs remote code on your machine at session start, and the plugin's README does not say so.
Reviewed by Claude (AI-assisted review), 2026-11-21
1 low-severity notes (informational, do not affect the result)
credential-access: Touches credentials or secrets low
scripts/maintenance-runner.py:119
OWASP LLM LLM03 Supply ChainOWASP Agentic ASI03 Identity and Privilege AbuseOWASP Agentic ASI04 Agentic Supply Chain VulnerabilitiesMITRE ATLAS AML.T0055 Unsecured CredentialsMITRE ATLAS AML.T0083 Credentials from AI Agent Configuration
resolve_executable(["claude", "--help"], dict(os.environ)),
What this means: Reads files or environment holding keys, tokens or sessions.
What you can do: Confirm the tool needs this; otherwise do not install.
Dispute this result
Maintainer and think this is wrong? Open a dispute on GitHub with the target id plugin-zilliztech-memsearch-plugins-claude-code-0bce1c.