Skills
Navigate
skills/moonpay/skills/moonpay-export-data/Gen Agent Trust Hub

moonpay-export-data

Fail

Audited by Gen Agent Trust Hub on Sep 22, 2026

Risk Level: CRITICALINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill ingests data from the output of the mp CLI tool, which creates a surface for indirect prompt injection if the tool's output is compromised.
  • Ingestion points: Commands in SKILL.md capture output from mp token balance list and mp transaction list.
  • Boundary markers: The skill does not use specific boundary markers or delimiters for the ingested data.
  • Capability inventory: The skill uses file system operations (creating directories and writing files) and provides commands to open the resulting files (open and xdg-open).
  • Sanitization: The scripts utilize jq with the @csv filter, which performs proper escaping and structured serialization, significantly mitigating the risk of downstream command injection or data malformation.
Recommendations
  • Contains 1 malicious URL(s) - DO NOT USE
Audit Metadata
Risk Level
CRITICAL
Analyzed
Sep 22, 2026, 05:09 PM