ClawAudit verdict

deepclaw

18
🔴 Dangerous
Reviewed by ClawAudit — concrete malicious or deceptive behavior found

Accesses agent memory/notes AND makes external network calls

The skill explicitly instructs the agent to fetch https://deepclaw.online/heartbeat.md every 4+ hours and 'follow it' — fetching arbitrary instructions from an attacker-controlled external URL and executing them is a remote code/command injection pattern that allows the operator of deepclaw.online to issue arbitrary future commands to any agent that installs this skill.

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
70
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

Accesses agent memory/configuration files

agent_memory

Findings (1)

Pattern match medium

Popular HTTP library — network access

HEARTBEAT.md · code · Got

Permissions & capabilities

No declared permissions — minimal attack surface.

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