The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill synthesizes specifications from untrusted sources and publishes them to an external issue tracker for automated processing. Ingestion points: The agent reads the current conversation context and performs codebase exploration to synthesize the spec (SKILL.md). Boundary markers: The skill does not provide delimiters or instructions to ignore embedded commands in the synthesized output. Capability inventory: The skill is capable of publishing synthesized text to the project issue tracker (SKILL.md). Sanitization: No sanitization or validation logic is defined to clean the synthesized content before it is published and labeled for automated execution.

to-spec