data

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 1.00). The skill's examples and table schemas explicitly query and return raw string/memory contents (e.g., "SELECT addr, content FROM strings WHERE content LIKE '%password%';" and read_cstr) which requires the LLM to emit secret values verbatim, creating an exfiltration risk.

MEDIUM W013: Attempt to modify system services in skill instructions.

• Attempt to modify system services in skill instructions detected (high risk: 0.90). This skill explicitly instructs the agent to perform irreversible on-disk modifications to binaries (e.g. UPDATE bytes, INSERT/commit patches) which change the machine's filesystem state.