pp-claude-agent-sdk-python-docs

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

• Third-party content exposure detected (low risk: 0.10). The skill’s runtime workflow reads only first-party Claude Code documentation fetched over HTTPS (e.g., via the CLI pages/search/context/guide/symbol/examples commands), not arbitrary outsider-authored free text pushed into a queue/feed or ticket/email/chat body.

MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).

• Potentially malicious external URL detected (high risk: 0.90). The skill requires installing a CLI via remote Go module fetches that will download and build remote code at runtime (go install github.com/mvanhorn/printing-press-library/library/developer-tools/claude-agent-sdk-python-docs/cmd/claude-agent-sdk-python-docs-pp-cli@latest and go install github.com/mvanhorn/printing-press-library/library/developer-tools/claude-agent-sdk-python-docs/cmd/claude-agent-sdk-python-docs-pp-mcp@latest), which constitutes fetching and executing external code that the skill depends on.