The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: The skill refers to and provides installation instructions for an external tool hosted on the author's GitHub repository (https://github.com/konglong87/anysearch.git).
[COMMAND_EXECUTION]: The skill uses the Bash tool to locate and execute a Python script (anysearch_cli.py). It performs a path discovery process across multiple directories in the user's home folder and uses python3 -c to find the package's location via the standard library.
[INDIRECT_PROMPT_INJECTION]: The skill is vulnerable to indirect prompt injection due to its core functionality of processing external data.
Ingestion points: The skill ingests untrusted data from the web using WebSearch, Exa MCP, and the anysearch CLI's search and extraction commands.
Boundary markers: No specific delimiters or "ignore embedded instructions" warnings are defined for the agent to use when handling retrieved search results.
Capability inventory: The skill possesses Bash, Write, and Agent capabilities, which could be abused if the agent follows instructions embedded in search data.
Sanitization: The instructions do not specify any sanitization, filtering, or validation of the retrieved web content before it is written to local markdown files in the docs/ directory.

pm-search