pp-claude-agent-sdk-python-docs

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

• Third-party content exposure detected (high risk: 0.85). The required workflow explicitly fetches public Claude Code docs over HTTPS at runtime (outsider-authored web content) and then returns extracted docs/examples/citations via the --agent JSON output, which the agent would ingest into its LLM context.

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

• Potentially malicious external URL detected (high risk: 0.80). The CLI explicitly reads the public Claude Code docs over HTTPS at runtime and injects that fetched documentation into agent context (thus influencing prompts/instructions) — referenced as "public Claude Code docs over HTTPS" in SKILL.md:115-118.