The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill ingests and processes content from multiple external repository files, such as CONTEXT.md, requirements specifications (SRS), and architecture guidelines. These files represent an attack surface where malicious instructions could be embedded to influence the agent's logic during design tasks.
Ingestion points: Reads CONTEXT.md, docs/architecture/soup.md, .guardrails/config.yaml, and SRS files.
Boundary markers: No explicit delimiters or instructions to ignore embedded commands are used when interpolating this data into the prompt.
Capability inventory: The skill can write files to the repository (docs/architecture/, docs/adr/) and execute several local shell scripts.
Sanitization: No sanitization or validation of the ingested text is performed before processing.
[COMMAND_EXECUTION]: The skill executes various local shell scripts located within the project's .guardrails/ directory, including check-trace.sh, new-id.sh, find-items.sh, and check-units.sh. These are used to automate ID generation and trace validation.

design-architecture