The Agent Skills Directory

[COMMAND_EXECUTION]: The skill instructs the agent to use the sdd doc command-line interface for tasks like entity lookup, call graph analysis, and impact assessment. These commands are part of the skill's primary intended functionality and operate on the local file system.
[PROMPT_INJECTION]: The skill acts as an ingestion point for documentation data (e.g., codebase.json, docs/ directory) that is generated from project source code, making it susceptible to indirect prompt injection.
Ingestion points: Documentation files such as codebase.json and markdown files within the docs/ directory (referenced in SKILL.md).
Boundary markers: There are no explicit instructions or delimiters provided in the skill files to ensure the agent ignores or sanitizes instructions that might be embedded in the documentation content.
Capability inventory: The agent has access to various analysis and query commands via the sdd tool, which could be misdirected if the input documentation is malicious.
Sanitization: No sanitization or validation logic is defined in the skill for the documentation content it processes.

doc-query