review-work
Pass
Audited by Gen Agent Trust Hub on Oct 22, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted external data which could contain malicious instructions designed to influence the agent's review verdict or actions.
- Ingestion points: Data is loaded via
get_work_unit,get_task, andlist_task_comments(SKILL.md, Steps 1 & 4). This includesacceptance criteria,devInfo(which containstestResultsandfilesChanged), and existing task comments. - Boundary markers: The instructions lack explicit delimiters or "ignore embedded instructions" warnings when processing potentially attacker-influenced task content.
- Capability inventory: The skill has significant write capabilities to the project management system, including
update_task,create_task_comment,batch_create_tasks, andupdate_work_unit(SKILL.md, Step 5). - Sanitization: No sanitization, escaping, or validation of the ingested strings is performed before they are interpolated into the agent's reasoning process for generating verdicts like "APPROVED" or "NEEDS REWORK".
Audit Metadata