The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill processes untrusted content from the local workspace (source code, configuration files, and existing markdown documentation), which could potentially contain malicious instructions intended to mislead the agent.
Ingestion points: Reads README.md, CHANGELOG.md, ROADMAP.md, types*.ts, and config.* from the local repository.
Boundary markers: The instructions do not define specific delimiters or "ignore" rules for data read from these files.
Capability inventory: The skill has the ability to read files, execute git commands (including commit and push), and generate documentation reports.
Sanitization: There is no evidence of sanitization or filtering applied to the content extracted from project files before it is processed or used in reports.
[COMMAND_EXECUTION]: The skill uses standard developer utilities like git (for diffing, status, committing, and pushing) and find (for file discovery). These operations are restricted to the context of managing the local repository.

docs-sync