pp-parallel

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

• Third-party content exposure detected (medium risk: 0.30). The skill’s required runtime workflow explicitly ingests outsider-authored free text from the user question (via the recall "<user's question>" --agent decision tree) and then uses it to drive web research/extraction by calling Commands like tasks runs-post/extract/findall, meaning attacker-controlled text can be consumed without selecting a specific pre-authored item first.

MEDIUM W009: Direct money access capability detected (payment gateways, crypto, banking).

• Direct money access detected (high risk: 1.00). The skill exposes a specific financial operation: "service account-add-balance — Charge the organization's default payment method and add the amount to the prepaid credit balance." That is an explicit payment/charge API (directly moves money onto the organization's prepaid balance). The doc also warns about using Account balance add for unattended spends and describes Account commands requiring OAuth, confirming this CLI can perform authenticated billing actions. This meets the "Direct Financial Execution" criteria.