The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: The skill requires the installation of an external binary tool goplaces from a third-party Homebrew tap (steipete/tap/goplaces). This dependency is hosted on GitHub but is not from a verified or trusted organization listed in the security guidelines.
[COMMAND_EXECUTION]: The skill's primary functionality relies on executing the goplaces CLI binary. It passes user-provided strings (like search queries and place IDs) directly to the command line, which could lead to argument injection if the underlying tool does not handle inputs securely.
[CREDENTIALS_UNSAFE]: The skill requires the GOOGLE_PLACES_API_KEY environment variable. The skill documentation also mentions an optional GOOGLE_PLACES_BASE_URL variable, which allows redirecting API requests. If this is pointed to a malicious endpoint, the API key could be exposed to an external party.
[PROMPT_INJECTION]: The skill is subject to indirect prompt injection risks as it processes data from the Google Places API (including user-generated reviews and place descriptions).
Ingestion points: Data returned by goplaces search, details, and reviews commands.
Boundary markers: No specific delimiters or safety instructions are provided to the agent to treat API output as untrusted data.
Capability inventory: The agent can execute system commands using the goplaces binary.
Sanitization: The skill does not describe any sanitization or filtering of the content retrieved from the external API before presenting it to the agent.

goplaces