Security review
⚠ Flagged1 finding(s); flagged for manual review. · v0.1.0 · scanned 2026-06-30 How review works →
- • Prompt-injection patterns
- • Secret / credential exfiltration
- • Dangerous shell & filesystem operations
- • Untrusted network calls
- • Known-malicious package signatures
- high Destructive filesystem operation.
What it can access
- ● Network access Used
- ✓ Filesystem access No
- ✓ Shell / process execution No
- ✓ Environment & secrets No
- ✓ Dynamic code execution No
From automated source analysis of v0.1.0. “Used” means the capability is present in the source — more access means more to trust, not that it’s unsafe.
What this report covers
- Prompt injection, instructions hidden in tool descriptions or outputs that try to hijack the agent.
- Secret exfiltration, code paths that read credentials or environment and send them off-box.
- Dangerous tool calls, unguarded shell, filesystem, or network access.
Automated scanning runs on every published version before it can list publicly. Full methodology →