The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill processes several external data sources which could serve as injection vectors if their content is influenced by an attacker.
Ingestion points: The skill reads data from Operational/DR-Plan-*.html, CLAUDE.local.md, Operational/IRP-*.html, PRD/*.html, and files within the Architecture/ directory.
Boundary markers: No specific boundary markers or instructions to ignore embedded commands within the processed files are defined in the skill logic.
Capability inventory: The skill has the capability to write local files (Operational/Recovery-Procedures-{ProductName}-{Date}.html) and present generated content directly to the agent's context.
Sanitization: There are no explicit instructions to sanitize or validate the content extracted from the HTML and Markdown files before it is interpolated into the generated runbooks.

pmstudio-recovery