shift-left-testing
Pass
Audited by Gen Agent Trust Hub on Sep 17, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it processes untrusted content from external sources.
- Ingestion points: The skill reads Story descriptions, Acceptance Criteria, and user comments from Jira via the
bun run jira:sync-issuescommand as described inSKILL.mdandreferences/backlog-selection.md. - Boundary markers: There are no explicit instructions or delimiters found in the prompts to ensure the agent ignores potentially malicious instructions embedded within the Jira issue content.
- Capability inventory: The skill utilizes the
aclitool to perform significant mutations on Jira issues, including updating descriptions, changing fields, modifying labels, transitioning issue statuses, and posting comments as detailed inreferences/handoff-protocol.md. - Sanitization: The instructions do not define any sanitization, validation, or escaping protocols for the content ingested from the Jira issues before it is used to drive the agent's logic.
Audit Metadata