The Agent Skills Directory

[COMMAND_EXECUTION]: The skill uses local shell commands, specifically git remote get-url origin and git log, to retrieve repository details and history. These actions are aligned with the skill's stated purpose.
[PROMPT_INJECTION]: The skill contains an attack surface for indirect prompt injection.
Ingestion points: Untrusted data enters the context through git log output, which contains commit messages and author names provided by external contributors.
Boundary markers: There are no instructions to use delimiters or to treat commit data as untrusted text.
Capability inventory: The skill performs command execution via git subprocess calls.
Sanitization: There is no evidence of sanitization or filtering of the commit messages before they are processed by the agent.

wiki-changelog