The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and analyze external data from URLs or file paths provided by the user, creating a surface for indirect prompt injection.
Ingestion points: The argument-hint field in the frontmatter specifies that the skill takes a URL or file path as input.
Boundary markers: There are no instructions provided to the agent to treat external content as data only or to ignore instructions embedded within the source content.
Capability inventory: The skill's primary function is to audit and rewrite content, which requires deep processing of the untrusted input.
Sanitization: The instructions do not include any steps for sanitizing or validating the input data to prevent malicious instruction execution.

geo-optimizer