pu

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 1.00). This skill explicitly instructs the agent to pass the user's arguments verbatim to another skill, which can force the LLM to include any user-supplied secrets (API keys, tokens, passwords) in its output, creating an exfiltration risk.

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

• Third-party content exposure detected (medium risk: 0.30). /pu is a pure alias that immediately forwards the user’s arguments verbatim to the pickup skill, so the only LLM-ingested text at this runtime path is user-provided free text via the Skill tool invocation.