oci-functions-troubleshoot

Pass

Audited by Gen Agent Trust Hub on Jul 14, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface as it ingests untrusted data from OCI logs and error messages.
  • Ingestion points: The troubleshooting sequence in SKILL.md and reference files requires the agent to analyze user-provided error text and application telemetry.
  • Boundary markers: The instructions lack boundary markers or warnings to the agent to ignore instructions embedded in the logs.
  • Capability inventory: The agent is directed to use the fn and oci CLI tools to perform diagnostic checks like 'fn inspect context'.
  • Sanitization: There is no defined process for sanitizing or validating the ingested logs before analysis.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 14, 2026, 04:28 AM
Security Audit — agent-trust-hub — oci-functions-troubleshoot