ClawAudit verdict

claude-mem

45
🟠 Risky
Significant concerns — only install if you understand the risks

Accesses agent memory/notes AND makes external network calls

Primary install method is `curl -fsSL https://install.cmem.ai/openclaw.sh | bash`, piping a script from a custom domain (not a known code host) that installs a persistent background worker on port 37777 handling agent memory; the opaque install domain and persistent service warrant caution.

Automated static analysis — not a human review. ClawAudit flags capabilities, not confirmed intent, and can produce false positives. Disagree with this verdict? Use Dispute below.

0
security
30
transparency
80
maintenance

What it does

These are capability combinations: each listed behavior occurs in the skill, but ClawAudit detects co-occurrence — it does not verify that one flows into another. Read the code to confirm a live chain.

Capability combination critical

Accesses agent memory/notes AND makes external network calls — may leak personal data

LLM02 · LLM07 · ASI03 · ASI06

Capability combination high

Accesses credentials AND makes external network calls — potential credential theft

LLM02 · ASI03

Capability combination high

Accesses agent memory AND makes external network calls — may leak conversation history

LLM02 · LLM07 · ASI06

Permission integrity

Makes network requests but does not declare curl/wget in required binaries

network_out

Code accesses API keys/tokens but declares no environment variables

credential_access

Installs packages at runtime — transitive dependencies are not auditable

package_install

Accesses agent memory/configuration files

agent_memory

Findings (8)

Pattern match critical

Pipe-to-shell pattern (curl | sh) — supply chain attack vector

SKILL.md · code · curl -fsSL https://install.cmem.ai/openclaw.sh | bash

Pattern match critical

Pipe to bash — executes piped content as shell commands

SKILL.md · code · | bash

Pattern match high

Possible hardcoded credential

install.sh · prose · downgraded · API_KEY="${1#--api-key=}

Pattern match medium

References agent memory files

SKILL.md · code · MEMORY.md

Pattern match medium

References sudo — requests elevated privileges

install.sh · prose · downgraded · sudo

Pattern match medium

HTTP request to bare IP address — common in malicious payloads

install.sh · prose · downgraded · http://127.0.0.1

Pattern match medium

Accesses OpenClaw config/secrets directly

install.sh · prose · downgraded · ~/.openclaw/openclaw.json

Pattern match low

Popular HTTP library — network access

SKILL.md · prose · downgraded · Got

Why the tier is capped

Execution sink present in raw bytes (Hard Floor: class A/B/F). Final tier capped at Caution — cannot be lifted by any downgrade, example-payload opt-in, or allowlist.

Permissions & capabilities

No declared permissions — minimal attack surface.

network_outcredential_accesspackage_installagent_memory
Check another skill Browse the registry Auditing your own skills or configs? Use the API