aile-delivery-report
Pass
Audited by Gen Agent Trust Hub on Mar 6, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: Indirect prompt injection surface identified where untrusted content could influence agent behavior.
- Ingestion points: The skill ingests content from local files such as
docs/plans/{Story-Key}/analysis.md. - Boundary markers: The template
docs-templates/stage3-pr-description-template.mdlacks explicit delimiters or instructions to prevent the agent from following commands embedded in the source documents. - Capability inventory: The skill utilizes the
jira_update_issuetool to modify the state of external Jira stories. - Sanitization: There is no evidence of input sanitization or validation for the content extracted from the analysis files before it is processed by the agent.
Audit Metadata