The Agent Skills Directory

[PROMPT_INJECTION]: The skill contains instructions to ingest data from external context files, which constitutes a vulnerability surface for indirect prompt injection.
Ingestion points: The agent is directed to read from .agents/product-marketing-context.md and .claude/product-marketing-context.md.
Boundary markers: There are no defined delimiters or specific instructions provided to the agent to disregard potential instructions embedded within the ingested context files.
Capability inventory: The skill files contain no subprocess executions, dynamic code evaluations (eval/exec), network requests, or file-system write operations.
Sanitization: No sanitization, validation, or filtering of the content from the external context files is specified in the skill instructions.

onboarding-cro