ClawHub
Back to skill

Security audit

zambo

Security checks for vulnerabilities and agentic risk

Overview

Zambo’s remote tools fit its purpose, but its full-context sharing instructions omit important privacy and publication controls.

Use sanitized, narrowly scoped inputs. Before sending private code or conversation context, review Zambo’s privacy policy and sharing settings. Inspect handovers before publication; automatic redaction can miss private information, and withdrawing a page cannot recall downloaded copies. See [handover guidance](https://zambo.dev/handover/). Receipt verification establishes integrity, not confidentiality.

A.I.G

Vulnerability Patterns
  • Skill Instruction HijackingAlters the agent's session goals or safety constraints when the skill loads
  • Agent Memory PoisoningWrites attacker-controlled rules into memory that affect later sessions
  • Remote Payload Retrieval and ExecutionFetches external code whose behavior can change after review
  • Embedded Malicious CodeShips malicious scripts inside the skill and executes them locally
  • Unauthorized Access and Privilege EscalationObtains permissions beyond the task's legitimate needs

SkillSpector

Vulnerability Patterns
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • Output HandlingUnvalidated Output Injection, Cross-Context Output, Unbounded Output
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (2)

The workflow sends job content to a third-party service without a privacy warning.

Medium
Category
Output Handling
Confidence
93% confidence
Finding

The workflow directs agents to send job content to an external service without defining privacy boundaries, redaction requirements, or when user approval is needed. Its suggested uses include code audits, secret scans, persistent memory, and handovers containing full context, increasing the chance of disclosing confidential code, credentials, or personal information; receipt integrity does not establish confidentiality or appropriate retention.

Content

No source excerpt is available for this finding.

Unbounded Resource Access

Medium
Category
Excessive Agency
Confidence
80% confidence
Finding

Skill allows unbounded resource consumption (API calls, storage, compute). Without rate limits or quotas, a compromised or misbehaving agent can cause denial-of-service or cost overruns.

Content

Scanner excerpt · SKILL.md (reported line 68)May include surrounding context.

md
## Pricing

- Free: 20 calls and 1 wrap-up free every day. Picking up in another AI is always free.
- Day Pass: $0.99 for unlimited calls for 24 hours (one payment, no renewal; agents pay USDC on Base via x402, humans pay by card or PayPal).
- Zambo Pass: $29 for 30 days or $290 for 365 days, one payment.
- $ZAMBO holders: $19 for 30 days.

Static analysis

No suspicious patterns detected.