The Agent Skills Directory

[COMMAND_EXECUTION] (SAFE): The skill executes specific commands through the gog CLI tool. These operations are scoped to Google Slides management and do not exhibit signs of arbitrary or malicious command execution.
[PROMPT_INJECTION] (LOW): The skill is susceptible to indirect prompt injection. Ingestion points: Untrusted data enters the context via Markdown files in create-from-markdown and existing slide content in read-slide. Boundary markers: No explicit delimiters or instructions are used to separate user data from agent instructions. Capability inventory: The skill can execute shell commands via gog and perform file-write operations through the export command. Sanitization: There is no evidence of input validation or content filtering before the data is processed or interpolated.

gslides