The Agent Skills Directory

[COMMAND_EXECUTION]: The skill utilizes the Bash tool to execute Git commands (git diff, git status, git log) to identify uncommitted changes in the workspace.\n- [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it reads and processes the content of untrusted local files (SKILL.md, README.md, and references/ files).\n
Ingestion points: Content is read from SKILL.md, README.md, and files within the references/ directory as specified in the review process.\n
Boundary markers: The instructions do not define specific delimiters or warnings to ignore embedded instructions within the processed data.\n
Capability inventory: The skill has the ability to write to the file system using the Edit tool and execute shell commands via the Bash tool.\n
Sanitization: There is no evidence of sanitization or validation of the content retrieved from the files before it is passed to the review agent.

skill-review