agentic-doc-parse-and-extract

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

• Third-party content exposure detected (high risk: 0.90). The skill explicitly ingests documents from arbitrary URLs (e.g., "adp extract url " and "adp parse url " in SKILL.md and references/commands.md, including URL-list batch files), meaning untrusted third‑party web content is fetched and interpreted as part of the agent's workflow and can materially influence subsequent actions.

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

• Potentially malicious external URL detected (high risk: 0.90). The skill's runtime installation steps instruct executing remote code (curl -fsSL https://raw.githubusercontent.com/laiye-ai/adp-cli/main/scripts/adp-init.sh | bash and Invoke-WebRequest https://raw.githubusercontent.com/laiye-ai/adp-cli/main/scripts/adp-init.ps1; and downloading/executing binaries from https://laiye-devops.oss-cn-beijing.aliyuncs.com/release/adp/cli/v1.10.0/...), which fetches and runs external scripts/binaries that the skill requires on first execution.