braindump

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 0.90). The skill proactively instructs the agent to silently capture and later retrieve arbitrary contextual data (including environment configs, variables, API specs) into plain-text notes and to display/search that content, which enables storing and outputting secret values verbatim.

CRITICAL E005: Suspicious download URL detected in skill instructions.

• Suspicious download URL detected (high risk: 0.90). Suspicious: this is a direct raw GitHub link to an install.sh in an individual/unverified repository and the skill explicitly instructs using curl | bash to execute a remote shell script, a high-risk pattern for distributing malware.