The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill processes potentially untrusted markdown files from project directories to generate baseline inventories and change control records.
Ingestion points: The skill instructions in SKILL.md (Step 1) require reading all *.md artifacts in projects/<ProjectName>/<phase>/<document>/, as well as vision.md and stakeholder_register.md.
Boundary markers: The skill lacks explicit instructions for the agent to use delimiters or specific warnings to ignore instructions that might be embedded within the requirement identifiers or descriptions being processed.
Capability inventory: The skill utilizes file system read, search, and write capabilities to process input artifacts and generate the requirements_baseline.md and change_control_process.md outputs.
Sanitization: There is no evidence of validation or sanitization of the content extracted from the markdown files before it is processed or written to output files.

08-requirements-management