The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill reads and parses user-controlled story files and sprint plans to validate implementation requirements. Maliciously crafted content in these files could attempt to override the agent's instructions.\n
Ingestion points: The skill loads data from production/epics/**/*.md, production/sprints/, and various architecture documents in the docs/ and design/ directories.\n
Boundary markers: There are no explicit delimiters or system instructions defined to prevent the agent from following instructions embedded within the analyzed story text.\n
Capability inventory: The skill is granted access to Read, Glob, Grep, and Agent tools. While the reference file claims it is read-only, the main SKILL.md instructions suggest that the agent may perform direct implementation changes if requested, creating a broader impact surface for injection attacks.\n
Sanitization: No sanitization or structural validation is performed on the extracted strings before they are processed as part of the agent's reasoning loop.

story-readiness