The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process untrusted data from the local repository and user descriptions to generate bug reports.
Ingestion points: The skill utilizes tools such as Read, Grep, and Glob to extract content from repository files and user-provided descriptions (defined in references/claude-skill.md).
Boundary markers: There are no explicit delimiters or specific instructions to ignore potentially malicious embedded commands within the ingested content.
Capability inventory: The skill directs the agent to write files to the project directory (production/qa/bugs/) and execute project-specific verification checks and test automation routines (references/claude-skill.md).
Sanitization: No evidence of sanitization, validation, or escaping of ingested codebase content is present before processing.
[COMMAND_EXECUTION]: The instructions direct the agent to run the "repository's available checks" and execute the "verified Unity automation route" to generate NUnit XML results. This workflow relies on the execution of shell commands or scripts defined within the project repository to verify bug fixes.

bug-report