The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill processes potentially untrusted external content and client-provided instructions, which creates a surface for indirect prompt injection.\n
Ingestion points: The skill ingests data from targeted_candidates.json (specifically the excerpt field containing external news content) and the brief.md file.\n
Boundary markers: The instructions do not define specific delimiters or instructions to ignore potential commands embedded within the input signals or the client brief.\n
Capability inventory: The skill's capabilities are limited to file system read and write operations for pipeline artifacts. It has no network access or ability to execute arbitrary system commands.\n
Sanitization: The skill does not implement sanitization or filtering for the text content it processes.

newsjack-triage