The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill processes data from external files which serves as an ingestion point for untrusted instructions. \n
Ingestion points: The skill reads from cleaned-requirements/issues.md to extract answers provided by users. \n
Boundary markers: The instructions do not define specific delimiters or instructions to the agent to ignore any embedded commands within the issues.md content. \n
Capability inventory: The skill possesses Read, Write, and Bash capabilities, which could be leveraged if the agent were to follow instructions embedded in the requirements data. \n
Sanitization: The skill lacks explicit validation or sanitization mechanisms for the data retrieved from input files before it is merged into the clarified requirements.

req-merger