The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill's primary function involves processing user-provided source text for translation and review, creating a surface for potential indirect prompt injection attacks. * Ingestion points: Untrusted data enters the agent context via 'Source text' inputs during the translation and review workflow defined in SKILL.md. * Boundary markers: The instructions lack explicit directives for the agent to use delimiters or security-focused boundary markers when handling external content. * Capability inventory: The skill is limited to reading and searching local files; it lacks capabilities for arbitrary command execution, network exfiltration, or persistence. * Sanitization: There are no specified sanitization or filtering protocols for external content beyond linguistic quality checks.
[NO_CODE]: The skill consists of Markdown documentation and does not include any executable scripts, binaries, or automated package installations.

language-standards