The Agent Skills Directory

[SAFE]: The skill utilizes implicit IAM identity for authentication to OCI Object Storage, which prevents the need for hardcoded API keys or secrets within notebooks, adhering to security best practices.
[SAFE]: External references point to official Oracle samples on GitHub, which are recognized as trusted sources for documentation and examples.
[SAFE]: No malicious patterns such as prompt injection, code obfuscation, or unauthorized remote code execution were detected.
[INDIRECT_PROMPT_INJECTION]: The skill describes functionality to ingest data from external OCI buckets, which is a common pattern for data tools.
Ingestion points: Data loading operations via spark.read.load described in SKILL.md.
Boundary markers: Not present in the provided templates.
Capability inventory: The skill allows Spark SQL execution, file writing to cloud storage, and utilizes the Bash tool as defined in the frontmatter.
Sanitization: No specific sanitization or validation logic is included in the brief examples provided.
This represents a standard surface for processing external data and does not indicate malicious intent.

aidp-object-storage