The Agent Skills Directory

[PROMPT_INJECTION]: The skill includes instructions intended to override the agent's standard operational behavior. Specifically, the 'CRITICAL: Auto-start on load' header and subsequent instructions command the agent to skip summarization and explanation steps, immediately transitioning to task execution.
[INDIRECT_PROMPT_INJECTION]: The skill processes untrusted external data which could contain malicious instructions.
Ingestion points: The skill automatically reads from about-me.md if present and accepts user-uploaded files such as LinkedIn profile PDFs and screenshots.
Boundary markers: The instructions lack boundary markers or explicit delimiters to separate the external data from the skill's instructions.
Capability inventory: The skill generates profile content (headline, about, experience) and image generation prompts based on the ingested data. It does not possess network access or file-writing capabilities.
Sanitization: There is no evidence of sanitization or filtering applied to the external content before it is used to generate profile copy or design briefs.

profile-optimizer