The Agent Skills Directory

[PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because its core functionality involves the systematic ingestion and analysis of external, potentially untrusted codebase data.
Ingestion points: The skill performs a 'silent scan' of the project territory in Stage 1 (references/stage-1-known-knowns.md) and a systematic sweep of all project files in Stage 4 (references/stage-4-unknown-unknowns.md).
Boundary markers: There are no instructions provided to the agent to use delimiters or to treat ingested code content as data that should not be followed as instructions.
Capability inventory: The agent has the capability to read any file in the project, invoke subagents for analysis, and generate interactive HTML/JS mocks and implementation prompts based on its findings.
Sanitization: No sanitization or validation of the content read from the codebase is specified before it is included in artifacts presented to the user.
[COMMAND_EXECUTION]: The skill directs the agent to utilize automated subagents to perform wide-ranging parallel scans of the project environment.
Evidence: references/stage-1-known-knowns.md instructs the agent to 'Use subagents in parallel — split the code the task touches among them and collect what they pin down.' This represents programmatic exploration of the filesystem.

explore-unknowns