The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted data from the questions.md file which governs the agent's research focus. This file could contain instructions designed to override the skill's factual research constraints.
Ingestion points: questions.md referenced in SKILL.md.
Boundary markers: Absent; the instructions do not use specific delimiters or warnings to ignore instructions within the input file.
Capability inventory: Coordination of specialized research agents, file system reading for code analysis, and file system writing for report generation.
Sanitization: Absent; the skill does not perform validation or sanitization of the input text before processing.

qrspi-research