project-manager

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

• Third-party content exposure detected (high risk: 0.90). The skill's MCP integration docs and SKILL.md (e.g., mcp/JIRA.md, mcp/GITHUB.md, mcp/LINEAR.md and the Asana/ClickUp workflow templates) explicitly instruct the agent to fetch and process user-generated content from third‑party project tools (issues, PRs, tasks, tickets) and to act on that content (generate code, triage, assign, run automations), which exposes the agent to untrusted, user-supplied data that can materially influence tool use and actions.

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

• Potentially malicious external URL detected (high risk: 0.90). The skill includes MCP runtime commands that fetch and execute remote packages (e.g., npx @modelcontextprotocol/server-github / https://github.com/github/github-mcp-server) which run remote code at runtime and feed context into the agent, so this is a required external dependency that can directly control prompts/execution.