The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill processes external data in the form of a requirements packet, creating a potential surface for instructions embedded in the input to influence agent behavior.
Ingestion points: The workflow in SKILL.md and references/planning-workflow.md relies on a "validated requirements packet" as the primary source for generating plans.
Boundary markers: No explicit delimiters or instructions to ignore embedded commands within the source data are provided to the agent.
Capability inventory: The skill is restricted to generating text artifacts and lacks dangerous capabilities like shell command execution or network exfiltration tools.
Sanitization: There is no evidence of sanitization or filtering logic applied to the input content before processing.
[EXTERNAL_DOWNLOADS]: The skill contains references to external documentation and professional standards.
Evidence: references/source-literature.md includes URLs for the IEEE Computer Society, SEBoK Wiki, Scrum Guides, and the Project Management Institute (PMI).
Context: These references are to well-known professional organizations providing official methodology documentation (SWEBOK, Scrum Guide, WBS principles) and are consistent with the skill's intended use for project management.

krt-delivery-navigator