The Agent Skills Directory

[COMMAND_EXECUTION]: The skill executes git log --oneline to retrieve the repository's commit history. This is a standard read-only command required for the skill's stated purpose.
[PROMPT_INJECTION]: The skill is vulnerable to indirect prompt injection because it processes untrusted data from git commit messages which could contain instructions intended to mislead the LLM agents. * Ingestion points: Commit messages and descriptions are ingested via git log in SKILL.md. * Boundary markers: No delimiters or instructions to ignore embedded commands are present in the prompt logic. * Capability inventory: The skill has the ability to execute git commands and write to the local file system (CHANGELOG.md). * Sanitization: There is no evidence of sanitization or escaping of the commit history content before it is passed to the analysis agents.

generate-changelog