The Agent Skills Directory

[COMMAND_EXECUTION]: The skill uses the Bash tool to execute the mappu CLI. The instructions specify a command construction pattern (e.g., mappu --near "<location>" "<search_term>") that directly interpolates user-provided strings into a shell command. Without explicit instructions for the agent to sanitize these inputs, this pattern is vulnerable to command injection if a user provides input containing shell metacharacters such as semicolons, backticks, or command substitutions.
[EXTERNAL_DOWNLOADS]: The skill relies on an external, non-standard binary named mappu. The documentation explicitly instructs the agent to ask the user to manually install this binary from an unspecified source if it is not found on the system path. This introduces a dependency on external, unverified software.
[PROMPT_INJECTION]: The skill is susceptible to indirect injection where malicious data provided as a 'location' or 'search_term' could be used to manipulate the execution environment via the shell command construction described above.
Ingestion points: User-supplied location and search terms via the agent's interactive context.
Boundary markers: None. The command uses quotes, but there are no instructions to prevent the agent from escaping those quotes via the user input.
Capability inventory: The skill has access to the Bash tool, which allows for arbitrary code execution on the host system.
Sanitization: No sanitization or input validation logic is described in the skill instructions.

mappu