The Agent Skills Directory

[PROMPT_INJECTION]: The skill is vulnerable to indirect prompt injection because it ingests untrusted data from multiple external source files and interpolates them into its generated outputs.
Ingestion points: The skill reads data from files located in ai-tools/command-briefs/, ai-tools/skills/, and ai-tools/agents/ (documented in SKILL.md and registration-procedure.md).
Boundary markers: No explicit delimiters or boundary markers are used when interpolating untrusted data into the guide templates or roster table.
Capability inventory: The skill performs file read and write operations across the ai-tools/ directory.
Sanitization: No sanitization, validation, or escaping of the ingested content is specified in the workflow.
[NO_CODE]: The skill consists exclusively of markdown instruction files and reference checklists. It does not include any scripts, binaries, or other executable code, reducing its overall risk profile.

dm-registrar