The Agent Skills Directory

[CREDENTIALS_UNSAFE]: The skill explicitly includes .env* files in its 'Change Categories' for analysis. Accessing environment files is a high-risk activity as they frequently contain sensitive information such as API keys, database credentials, and private tokens.
[COMMAND_EXECUTION]: The skill uses the Bash tool to run git diff and git log commands. These commands are executed using branch names provided as input (e.g., --base), which can lead to command injection if the branch names are not properly sanitized before being passed to the shell.
[PROMPT_INJECTION]: The skill is vulnerable to Indirect Prompt Injection because it processes untrusted data from the repository's git history and source files.
Ingestion points: Data enters the agent's context through git diff outputs, git log commit messages, and the content of modified source files.
Boundary markers: There are no specified delimiters or instructions to ignore embedded commands within the files being analyzed.
Capability inventory: The agent possesses the capability to execute shell commands (Bash), read arbitrary files (Read), and modify repository files (Write).
Sanitization: The skill does not describe any methods for filtering or sanitizing the content of the files or diffs before they are used to generate the final README content.

sc-readme