The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill facilitates the ingestion of external data from Google Slides, creating a potential vulnerability to indirect prompt injection.
Ingestion points: External presentation data is loaded into the agent's context via the gws slides presentations get command.
Boundary markers: The skill does not define specific delimiters or instructions to ignore embedded commands within the retrieved presentation content.
Capability inventory: The skill allows write operations including batchUpdate and create, which could be targeted if a malicious injection is successful.
Sanitization: No sanitization or content validation mechanisms are described for data retrieved from the Google Slides API.
[COMMAND_EXECUTION]: The skill's primary operation involves executing the gws binary on the host system. This is an expected behavior for this vendor's toolkit but represents the execution of a local CLI tool.

gws-slides