sharedev-init

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 1.00). The prompt requires reading settings.json (including a certificate) and explicitly embedding <domain> and <certificate> into generated CLI commands (e.g., sharedev init -d <domain> -c <certificate>), which forces the agent to include secret values verbatim in its output/commands.

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

• Third-party content exposure detected (high risk: 0.80). The skill explicitly pulls remote resources via sharedev commands (e.g., "sharedev init --yes ...", "sharedev docs download", "sharedev object-dev object pull --all") and installs/reads third-party skill/spec files (checks and edits SKILL.md in Step 5, Step 8 and Step 8.5), so externally provided/untrusted content could be ingested and influence agent behavior.