oraclecloud-rate-limits

Pass

Audited by Gen Agent Trust Hub on Sep 9, 2026

Risk Level: SAFEDATA_EXFILTRATIONINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [DATA_EXFILTRATION]: The skill instructions and code examples reference accessing the OCI configuration file at ~/.oci/config. This is a standard sensitive file path that stores OCI credentials such as tenancy OCIDs and private key references. This access is required for the OCI SDK to function as intended.
  • [INDIRECT_PROMPT_INJECTION]: The skill defines patterns for fetching and processing data from external OCI service APIs.
  • Ingestion points: The skill retrieves resource information (e.g., instance lists, compartment data) from OCI API endpoints in SKILL.md.
  • Boundary markers: None present in the provided code examples to delimit external data from instructions.
  • Capability inventory: The skill's allowed tools include Bash, Write, and Edit which could be targeted by malicious data.
  • Sanitization: The examples do not demonstrate validation or sanitization of data returned from the cloud provider.
  • [EXTERNAL_DOWNLOADS]: The skill requires the installation of the official oci Python SDK and the certifi package from the standard Python Package Index (PyPI).
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 9, 2026, 03:48 AM
Security Audit — agent-trust-hub — oraclecloud-rate-limits