The Agent Skills Directory

[COMMAND_EXECUTION]: The skill instructs the agent to execute shell commands using the git tool, specifically git diff origin/main...HEAD --name-only to identify changed files and git log to determine the age of specific comments. These are appropriate and expected actions for a tool designed to perform repository-based code audits.
[PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it is designed to process and analyze untrusted external data (the user's source code and configuration files).
Ingestion points: The agent reads the content of source code files, dependency manifests (like package.json or requirements.txt), and documentation files found within the user's repository.
Boundary markers: There are no explicit instructions or delimiters defined to prevent the agent from being influenced by instructions embedded within comments or code in the analyzed files.
Capability inventory: The skill's capabilities are limited to reading local files and running informational git commands. It does not possess network access, file modification rights, or the ability to execute code from the files it reads.
Sanitization: The skill does not implement any sanitization or validation logic for the content it ingests from the scanned repository.

code-smell-detection