The Agent Skills Directory

[COMMAND_EXECUTION]: The skill instructs the agent to execute several shell commands, including astrofy check --rule quality.types, astro check, tsc, lint, and npm build. These operations are consistent with the skill's stated purpose of reviewing code quality and verifying fixes in an Astro development environment.
[INDIRECT_PROMPT_INJECTION]: The skill possesses an attack surface for indirect prompt injection due to its data ingestion patterns and available capabilities.
Ingestion points: The agent reads project-level configuration files such as tsconfig.json, package.json, package-lock.json, and .astrofy/config/paths.json, as well as source code files (SKILL.md, examples/cases.md).
Boundary markers: There are no explicit instructions or delimiters defined to prevent the agent from following instructions potentially embedded within these project files.
Capability inventory: The skill has the authority to execute shell commands (astrofy, astro, tsc, npm) which could be misused if malicious instructions are injected into the analyzed files (references/technical.md).
Sanitization: No specific sanitization or filtering logic is mentioned for the content retrieved from the project directory before it is processed by the agent or passed to verification tools.

astrofy-code-quality