The Agent Skills Directory

[PROMPT_INJECTION]: The skill processes user-supplied 'artifact path(s)' to evaluate and validate content. This ingestion of untrusted data represents a potential surface for indirect prompt injection should those artifacts contain malicious instructions. \n- Ingestion points: 'artifact path(s)' and user questions used as input for subagent reviewers in Step 1. \n- Boundary markers: The skill does not specify delimiters or system instructions to distinguish artifact content from agent commands. \n- Capability inventory: The skill is capable of prompting users via AskUserQuestion and invoking secondary skills through the 'Skill tool'. \n- Sanitization: No explicit validation or escaping of the ingested artifact content is performed within the skill instructions.

validate-answer