Peekaboo

Fail

Audited by Snyk on Feb 28, 2026

Risk Level: HIGH
Full Analysis

HIGH W007: Insecure credential handling detected in skill instructions.

  • Insecure credential handling detected (high risk: 1.00). The prompt's examples embed plaintext secrets (e.g., peekaboo type "supersecret") in CLI commands, which would require the LLM to include secret values verbatim in its output.

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

  • Third-party content exposure detected (high risk: 0.80). The SKILL.md explicitly shows opening arbitrary web pages (e.g., peekaboo app launch "Safari" --open https://example.com) and using visual capture/analysis commands (peekaboo see / peekaboo image --analyze) to read and act on the rendered UI, which means the agent can ingest untrusted public web content that could influence subsequent clicks/typing.
Audit Metadata
Risk Level
HIGH
Analyzed
Feb 28, 2026, 05:57 PM