deal-operations-administrator

Pass

Audited by Gen Agent Trust Hub on Oct 5, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONNO_CODE
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted external data including opportunity details, product SKUs, and contract content from Order Forms or SOWs (SKILL.md, references/deal_desk_review.md). There are no boundary markers or instructions to treat this content as data rather than instructions. The agent is directed to perform actions based on this data, such as updating CRM records to 'closed-won booked' and routing approvals (SKILL.md, references/signature_closeout.md), which creates a potential vector for malicious instruction execution.\n- [NO_CODE]: The skill consists exclusively of informational Markdown files. It does not include any scripts, shell commands, or external package dependencies, which limits its ability to perform direct unauthorized actions.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 5, 2026, 05:26 AM