The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill is designed to process untrusted data from external sources such as websites and uploaded business documents, which creates a surface for indirect prompt injection.
Ingestion points: As described in the Sources section, the skill reads data from websites, B2B review sites, and user-provided documents including proposals and sales call transcripts.
Boundary markers: The instructions do not define specific delimiters or provide the agent with warnings to ignore instructions that might be embedded within the source materials.
Capability inventory: The skill is limited to performing text extraction, categorization, and drafting outreach lines; it has no permissions for network operations, file writing outside of reports, or shell command execution.
Sanitization: The instructions do not include steps for sanitizing, validating, or escaping content extracted from external sources before it is processed by the agent.

value-prop-lister