peekaboo-hardened

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 1.00). The prompt includes example commands that embed plaintext credentials (e.g., peekaboo type "supersecret") and describes typing arbitrary text into apps, which would require the agent to include secret values verbatim in generated commands/outputs, creating exfiltration risk.

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

• Third-party content exposure detected (high risk: 0.90). The skill's SKILL.md shows runtime flows that open arbitrary webpages (e.g., "peekaboo app launch "Safari" --open https://example.com") and then capture/inspect/analyze browser windows via commands like "peekaboo see" and "peekaboo image --analyze", so the agent will ingest untrusted public web content from arbitrary URLs and act (click/type) based on that content.