The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest, edit, and translate user-supplied text for clarity and tone alignment. This introduces an indirect prompt injection surface where instructions hidden in the processed data could attempt to influence the agent. However, the skill does not define or use any tools, file-writing capabilities, or network-request functions, which significantly limits the potential for exploitation.
Ingestion points: User-provided text for drafting, rewriting, and translating (SKILL.md).
Boundary markers: Absent.
Capability inventory: None detected across the skill's instructions and reference files.
Sanitization: Absent.
[EXTERNAL_DOWNLOADS]: The references/terminology.md file contains numerous reference links and pointers to external documentation from established organizations and well-known services (such as AWS, Microsoft, Google, GitHub, and the NIST OSCAL repository). These URLs serve as sources for preferred industry terminology and do not involve executable code or sensitive data operations.

clear-writing