The Agent Skills Directory

[COMMAND_EXECUTION]: The skill uses shell commands including git add, git commit, git branch, and pwd to manage the Git worktree and automate version control operations during the feature implementation process. These commands are consistent with the skill's stated purpose.
[PROMPT_INJECTION]: Vulnerability surfaces for indirect prompt injection are present as the skill incorporates external data into its reasoning.
Ingestion points: The skill reads implementation guidance from docs/clean-code-principles.md and processes user-supplied 'Action Items' and 'Acceptance Criteria' to determine its next steps.
Boundary markers: There are no explicit boundary markers or instructions to treat the content of the documentation file or user input as untrusted data.
Capability inventory: The agent has permissions to execute shell commands and invoke other functional skills, which could be exploited if malicious instructions are embedded in the ingested content.
Sanitization: No sanitization or validation logic is applied to the documentation or user inputs before they are used to guide the agent's actions.

implement-feature