The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted user input as a 'topic' to generate creative content. While there are no explicit boundary markers or delimiters defined to separate the user data from the core instructions, the skill does not possess any exploitable capabilities—such as subprocess execution, file system modification, or network requests—meaning an injection attempt would have no high-impact target.
[SAFE]: No obfuscation, hidden URLs, or malicious persistence mechanisms were identified. The instructions focus on creative output formatting and stylistic guidelines consistent with the stated purpose.

life-quotes