pp-juneoven

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 0.90). The playbook replay instructions require substituting Playbook.slots_resolved entries (which can include a "token") into command templates, which would force the LLM to emit secret tokens verbatim when generating/executing those commands.

CRITICAL E006: Malicious code pattern detected in skill scripts.

• Malicious code pattern detected (high risk: 1.00). The skill documentation exposes high-risk patterns: it stores live credentials/tokens, auto-backgrounds teach/write operations, and supports arbitrary webhook/feedback sinks that can POST outputs — together enabling credential exposure and covert data exfiltration.