root-cause-investigation
Pass
Audited by Gen Agent Trust Hub on Jun 24, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill follows standard analytical procedures for investigating metric changes and does not exhibit any malicious patterns, obfuscation, or unauthorized access attempts.
- [PROMPT_INJECTION]: The skill exhibits an attack surface for indirect prompt injection by ingesting untrusted data (historical metric values, granular breakdown data, and change logs) that the agent must process.
- Ingestion points: Metric historical values, dimensional data, and incident logs listed in the 'Inputs' section of
SKILL.md. - Boundary markers: Absent. The skill does not provide instructions to wrap external data in delimiters or warn the agent to ignore instructions embedded within the data.
- Capability inventory: The skill executes a local Python script
scripts/drilldown_analyzer.pyusing provided data. - Sanitization: Absent. There are no instructions to validate or filter the data sources before they are processed by the agent or passed to the script.
Audit Metadata