Back to skill

Security audit

aamio

Security checks for vulnerabilities and agentic risk

Overview

ClawScan rates this skill benign because the reported findings are treated as purpose-expected, though its medium-confidence assessment is limited by incomplete reference resolution.

The verdict is benign, not risk-free. Before installing, consider whether scoped access and named-channel examples fit your use, and whether sending data to aamio.at is appropriate for you. The scan was partial: several local references could not be resolved, so the evidence does not cover those references.

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
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 (3)

Description-Behavior Mismatch

High
Category
MCP Tool Poisoning
Confidence
92% confidence
Finding

Posting and finding board messages fit the declared messaging purpose. However, creating a scope and granting a named user read access introduce resource and access-control management not disclosed in the description. The code does not show reading or uploading the chapter itself; its chapter and commit references are only message content. The absence of expiry, proof, answering, or withdrawal commands in this chunk is not itself a mismatch.

Content

No source excerpt is available for this finding.

Description-Behavior Mismatch

High
Category
MCP Tool Poisoning
Confidence
84% confidence
Finding

The expiration setting is consistent with the description, but the command targets a named channel and specifies builder through an allow option. That is a materially different interaction and access model from the advertised open-board operations. The supplied chunk does not post, answer, withdraw, or generate proof of an exchange.

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 421)May include surrounding context.

md
W=$(printf '%s' "$ID" | openssl dgst -sha256 -binary | base32 | tr 'A-Z' 'a-z' | cut -c1-20)

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