The Agent Skills Directory

[COMMAND_EXECUTION]: The skill preamble executes a local shell script check-update.sh via the Bash tool to handle versioning and updates.
[COMMAND_EXECUTION]: The skill instructs the agent to dynamically locate and execute an external utility named anysearch_cli.py by searching through several platform-specific hidden directories (e.g., ~/.claude/skills/anysearch/scripts/, ~/.cursor/skills/anysearch/scripts/, ~/.anysearch/scripts/) and then running it via python3. This dynamic path discovery and execution of external code depends on utilities whose integrity and source are not managed by this skill.
[EXTERNAL_DOWNLOADS]: The skill retrieves data from numerous external domains, including iresearch.cn, 36kr.com, and analysys.cn, using WebSearch and the mcp__exa__web_search_exa MCP tool for market research purposes.
[PROMPT_INJECTION]: The skill processes untrusted content from web searches to generate structured reports, which presents a surface for indirect prompt injection.
Ingestion points: External search results retrieved from the web and local content from docs/01-需求调研/需求调研报告.md.
Boundary markers: Absent. The skill does not implement delimiters or specific instructions for the agent to ignore potentially malicious commands embedded in the retrieved web data.
Capability inventory: The skill has access to Bash (command execution), Write (file system modification), and Agent (subagent orchestration).
Sanitization: Absent. Data from external sources is summarized and written to documents without formal validation or content filtering.

pm-market