The Agent Skills Directory

[COMMAND_EXECUTION]: The skill uses the Bash and Exec tools to run build systems, execute tests, and validate tooling changes. These actions are performed using existing project configurations to fulfill the skill's primary purpose.
[PROMPT_INJECTION]: (Indirect Prompt Injection Surface) The references in build.md and test.md instruct the agent to analyze diagnostic output (logs) and apply fixes. This creates a surface where untrusted data from the execution environment could influence agent actions. Ingestion points: Build logs and test failure outputs in references/build.md and references/test.md. Boundary markers: Absent; there are no specific instructions to use delimiters or ignore embedded prompts in logs. Capability inventory: Bash (command execution), Write (file modification), and Task (subagent delegation) tools are available to perform actions based on log analysis. Sanitization: Absent; the skill does not include steps to sanitize or validate diagnostic content before the agent processes it for automated recovery.

dev-workflows