The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process untrusted user-provided text drafts for rewriting, which creates a surface for indirect prompt injection.
Ingestion points: User-supplied text drafts or AI-generated content passed to the agent for processing as described in SKILL.md.
Boundary markers: No explicit delimiters or instructions are provided to the agent to treat the input text as data rather than instructions.
Capability inventory: The skill utilizes the @rephrasy/mcp humanize tool and suggests structural rewriting of content.
Sanitization: No sanitization or filtering of the input text is mentioned before the agent processes or humanizes it.

bypass-gptradar