The Agent Skills Directory

[COMMAND_EXECUTION]: The skill uses the Bash tool to execute a wide range of shell commands for repository management and testing. This includes git operations (fetch, merge, push) and running language-specific test runners (npm, pytest, go test, rspec) identified through project file analysis.\n- [DATA_EXFILTRATION]: The skill performs legitimate network operations to synchronize code with remote servers, specifically through git push and creating pull requests via gh pr create. These actions are necessary for the skill's intended function and target the user's configured repository origins.\n- [PROMPT_INJECTION]: The skill presents a surface for indirect prompt injection because it is instructed to read and analyze the full content of modified source files during its 'Coverage Audit' and 'Pre-Landing Review' phases.\n
Ingestion points: Reads all changed files and diffs in Step 3 and Step 4 to identify logic gaps and structural issues.\n
Boundary markers: No delimiters or instructions are used to isolate untrusted file content from the agent's core instructions.\n
Capability inventory: The skill has access to Bash, Write, and Edit, allowing it to modify code and execute commands based on its analysis.\n
Sanitization: There is no explicit sanitization step for the content read from files before it is processed by the AI.

relay-ship