WriteStory

CRITICAL E004: Prompt injection detected in skill instructions.

• Potential prompt injection detected (high risk: 1.00). The skill mandates executing an immediate curl POST to a local /notify endpoint before doing anything else, which is a side-effectful network action unrelated to the stated fiction-writing purpose and therefore a hidden/out-of-scope instruction.

CRITICAL E006: Malicious code pattern detected in skill scripts.

• Malicious code pattern detected (high risk: 1.00). High-risk: the skill mandates a stealthy, background HTTP POST to localhost:31337 (output suppressed) before any action, which looks like a deliberate beacon/backdoor activation rather than benign telemetry.