The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill instructs the agent to read text content from After Effects layers using the ae_text tool to check for typos. This creates a surface where malicious instructions embedded in the typography could influence the agent's behavior.
[INDIRECT_PROMPT_INJECTION]: Ingestion points: The ae_text tool is used to read text from After Effects layers into the agent's context.
[INDIRECT_PROMPT_INJECTION]: Boundary markers: The skill does not provide specific instructions to use delimiters or ignore embedded commands when reading text from layers.
[INDIRECT_PROMPT_INJECTION]: Capability inventory: The skill utilizes After Effects automation tools such as ae_add_property, ae_set_property, and ae_add_keyframes to modify project content.
[INDIRECT_PROMPT_INJECTION]: Sanitization: There is no mention of sanitizing or validating the text content read from After Effects layers before the agent processes it.
[DYNAMIC_EXECUTION]: The skill provides JavaScript-based expression templates for After Effects, such as for typing cursors and scramble-and-decode effects. These snippets are used to generate procedural animations within the After Effects expression engine based on provided recipes.

ae-typography