oci-costs
Pass
Audited by Gen Agent Trust Hub on Aug 28, 2026
Risk Level: SAFE
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingests external data from OCI usage reports which are processed using shell commands.
- Ingestion points: Usage reports are downloaded from OCI Object Storage using
oci os object getand subsequently read usingheadandgunzip(SKILL.md). - Boundary markers: None. The instructions do not define specific delimiters for the content of the usage reports.
- Capability inventory: The skill has access to
shell,read_file,write_file,glob, andgreptools. - Sanitization: No explicit sanitization or validation is performed on the contents of the usage reports before they are inspected.
Audit Metadata