cirq

Pass

Audited by Gen Agent Trust Hub on Sep 15, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill provides instructions for importing quantum circuits from external formats, which represents an indirect prompt injection attack surface.
  • Ingestion points: Instructions in references/building.md detail how to import circuits from external strings using cirq.contrib.qasm_import.circuit_from_qasm and cirq.read_json.
  • Boundary markers: There are no boundary markers or instructions provided to the agent to treat imported content as data only or to ignore potential instructions embedded within the QASM or JSON files.
  • Capability inventory: The skill is configured with broad permissions, including Bash access and file system Write and Edit tools. This high capability tier increases the potential impact if an agent is influenced by malicious instructions in a processed circuit file.
  • Sanitization: The provided instructions do not include steps for sanitizing or validating the integrity of imported circuit files before processing.
  • [EXTERNAL_DOWNLOADS]: The skill facilitates the installation of quantum computing dependencies from official registries.
  • Evidence: The SKILL.md file contains instructions to install cirq, cirq-google, cirq-ionq, cirq-aqt, cirq-pasqal, and azure-quantum[cirq]. These packages are sourced from official repositories and established vendors (Google, Microsoft, etc.) and are consistent with the skill's primary purpose.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 15, 2026, 12:02 AM
Security Audit — agent-trust-hub — cirq