The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill establishes a workflow where the agent is instructed to read and synchronize documentation artifacts, creating an attack surface where malicious instructions embedded in project files could influence the agent's behavior.
Ingestion points: The agent is directed to read context artifacts from the conductor/ directory, including product.md, tech-stack.md, workflow.md, and tracks.md as specified in references/details.md.
Boundary markers: The skill does not provide specific instructions or delimiters to isolate content within these files or to warn the agent against following instructions found within them.
Capability inventory: The skill involves file read and write operations for maintaining documentation; no high-privilege tools or network operations are requested in the skill configuration.
Sanitization: The skill contains no logic for sanitizing or validating the content of the artifacts before they are ingested into the agent's context.
[NO_CODE]: The skill consists entirely of markdown documentation and templates. It does not contain any executable scripts, binaries, or configuration files that trigger automated code execution.

context-driven-development