ClawAudit verdict
nstbrowser-ai-agent
Receives external input AND uses eval
Browser automation skill using the nstbrowser-ai-agent CLI for anti-detection profile management; dynamic_eval capability is a hint but no concrete eval pattern appears in the content, and all operations serve the stated automation 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.
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.
Receives external input AND uses eval — the remote code-injection pattern (data-flow not verified)
LLM01 · LLM05 · ASI01 · ASI05
Permission integrity
credential_access
package_install
Findings (5)
Possible hardcoded credential
references/nst-api-reference.md · code · API_KEY="your-api-key-here
HTTP request to bare IP address — common in malicious payloads
references/troubleshooting.md · code · http://127.0.0.1
References sudo — requests elevated privileges
references/troubleshooting.md · code · sudo
apt-get install — installs system packages
references/troubleshooting.md · code · apt-get install
Opens WebSocket connection
SKILL.md · prose · downgraded · WebSocket
Permissions & capabilities
No declared permissions — minimal attack surface.
package_installcredential_accessnetwork_indynamic_eval Thanks — recorded.