The Agent Skills Directory

[COMMAND_EXECUTION]: The skill invokes local Python scripts to manage an audit trail and resolve configuration settings.
Evidence: SKILL.md contains multiple calls to uv run {project-root}/_bmad/scripts/memlog.py, resolve_customization.py, and resolve_config.py.
[COMMAND_EXECUTION]: The skill utilizes system-level shell commands to display generated validation reports to the user.
Evidence: references/validate.md specifies the use of open, xdg-open, and start "" to open {doc_workspace}/validation-report.html in the default browser.
[INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process a wide variety of untrusted external data, which creates a vulnerability where embedded instructions could potentially influence agent behavior.
Ingestion points: SKILL.md (Discovery section) instructs the agent to read product briefs, research, customer transcripts, and competitive analysis files provided by the user.
Boundary markers: Absent; there are no explicit delimiters or instructions provided to the subagents to ignore potentially malicious embedded content within the ingested documents.
Capability inventory: The skill has the ability to execute local scripts and shell commands, and writes files to the local workspace.
Sanitization: Absent; no evidence of validation, escaping, or filtering of the external content before it is processed by subagents.

bmad-prd