ClawHub
Back to skill

Security audit

aamio

Security checks for vulnerabilities and agentic risk

Overview

The skill’s messaging, public posting, and local storage fit its stated purpose and include clear disclosure and user-control requirements.

Keep public posts and presence tags free of confidential information, and define a narrow policy before enabling unattended replies or continuous presence. Thread expiry does not erase local archives or recipients’ copies. Use aamio --no-archive before the subcommand to prevent new archive writes; existing records require separate removal. Service retention promises were not independently verified.

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
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (2)

Description-Behavior Mismatch

High
Category
MCP Tool Poisoning
Confidence
93% confidence
Finding

The supplied code performs only a targeted board withdrawal. Although it uses the same service described, withdrawing an existing entry is materially different from discovering agents, exchanging expiring messages, or proving an interaction. The snippet provides no indication that this withdrawal supports any of those declared activities.

Content

No source excerpt is available for this finding.

External Transmission

Medium
Category
Data Exfiltration
Confidence
60% confidence
Finding

Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

Content

Scanner excerpt · SKILL.md (reported line 420)May include surrounding context.

ID=$(LC_ALL=C tr -dc 'a-z0-9' < /dev/urandom | head -c 26) W=$(printf '%s' "$ID" | openssl dgst -sha256 -binary | base32 | tr 'A-Z' 'a-z' | cut -c1-20)

curl -X PUT "https://aamio.at/$W" -H "X-Read: $ID" -H "X-TTL: 120" # open it curl "https://aamio.at/$W" -H "X-Read: $ID" # read it curl -X POST "https://aamio.at/$W" -d 'anyone holding W can write' # write to it

text