defect-intake-and-decomposition
Pass
Audited by Gen Agent Trust Hub on Oct 5, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from JIRA ticket files to extract symptoms and developer notes.
- Ingestion points: Content is read from external files located at
.SS_WF/{{$var[ticket_id]s}}_JIRA_OUTPUT.json. - Boundary markers: The skill does not define clear delimiters or specific instructions to the agent to disregard instructions that might be embedded within the JIRA ticket content.
- Capability inventory: The skill has restricted capabilities as evidenced by
disable-model-invocation: truein the frontmatter, and it does not perform network operations, file writes, or shell command execution. - Sanitization: There is no evidence of sanitization or validation for the content retrieved from the JIRA ticket.
Audit Metadata