The Agent Skills Directory

[PROMPT_INJECTION]: The skill uses directive language such as 'CRITICAL: Auto-start on load' and 'Do not summarise the process' to bypass the agent's default conversational behavior and force immediate execution of specific steps.- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process arbitrary user-provided content to create infographic briefs.- Ingestion points: The agent prompts the user to paste content from external sources such as newsletters, blogs, and research notes in Step 1 (SKILL.md).- Boundary markers: There are no boundary markers or instructions provided to the agent to treat the user-supplied content as data rather than instructions.- Capability inventory: The skill does not possess capabilities for network access, file system modification, or command execution; it is limited to generating text output.- Sanitization: No sanitization, filtering, or escaping mechanisms are defined for the user-supplied content before it is incorporated into the agent's reasoning process.

gemini-infographic