The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from external sources to generate writing profiles, creating a surface for potential injection attacks.
Ingestion points: The skill gathers 5 to 20 representative samples from external sources including X (Twitter) posts, articles, emails, and product documentation (SKILL.md).
Boundary markers: There are no explicit instructions or delimiters defined to ensure the agent ignores potential instructions embedded within the analyzed source materials.
Capability inventory: The skill uses the x-api tool to fetch external data and is designed to feed into downstream skills like crosspost and lead-intelligence which may have further execution capabilities.
Sanitization: The skill lacks instructions for sanitizing or filtering the content of the source samples before the agent processes them.

brand-voice