The Agent Skills Directory

[PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection where malicious instructions could be embedded in the text being processed. * Ingestion points: The skill reads and processes external text drafts and content for the purpose of humanizing the writing style as defined in SKILL.md. * Boundary markers: No delimiters or instructions are used to separate the content being analyzed from the agent's core instructions, increasing the risk that the agent may follow commands found within the text. * Capability inventory: The skill uses Read, Write, Edit, Grep, and Glob tools, providing a significant capability set that could be misused if an injection is successful. * Sanitization: There is no evidence of input validation or sanitization to ensure that the content being processed does not contain executable instructions or agent-directing prompts.

humanizer