The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill possesses a surface for indirect prompt injection by ingesting and processing untrusted external data from various sources.
Ingestion points: The skill reads and evaluates 'copy (ads, emails, posts, pages, scripts, briefs)', 'press quotes, reviews or testimonials', and content from the 'live site'.
Boundary markers: There are no explicit instructions to use delimiters or ignore instructions embedded within the processed external content.
Capability inventory: The skill uses tools including save-learning and save-to-brain to update persistent brand records and agent memory based on findings from the processed data.
Sanitization: The instructions do not specify any sanitization or validation of the external content before it is processed or used to update records.

claims-gate