The Agent Skills Directory

[COMMAND_EXECUTION]: The skill instructs the agent to execute shell commands such as 'git diff', 'git log', and 'git rev-parse' using user-supplied parameters. This creates a potential for command injection if inputs are not strictly validated.
[PROMPT_INJECTION]: The skill processes untrusted code diffs and project documentation, which exposes the agent to indirect prompt injection. Ingestion points: Data enters the context via 'git diff' output, commit messages, and specification files in the repository. Boundary markers: The sub-agents are not provided with explicit instructions to ignore embedded commands within the analyzed data. Capability inventory: The skill has the ability to read arbitrary files in the repository and execute git commands. Sanitization: The skill does not perform any escaping or validation of the ingested diff or documentation content.

code-review