rhdh-release-capacity-plan
Pass
Audited by Gen Agent Trust Hub on Oct 23, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from Jira issues and Google Calendar events that could contain malicious instructions designed to subvert agent behavior during report generation.\n- Ingestion points: Data is gathered from Jira issue summaries and descriptions via sprint and feature searches, and from event titles in the shared RHDH PTO calendar.\n- Boundary markers: The instructions do not define delimiters or safety guardrails to separate untrusted external content from the agent's core instructions when generating the plan summary.\n- Capability inventory: The agent has the ability to run local Python scripts and interact with the Jira and Google APIs using CLI tools, creating a surface where malicious data could influence actions or output.\n- Sanitization: No explicit sanitization, filtering, or validation of the retrieved summaries is performed before the data is processed or displayed in the final report.
Audit Metadata