The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill processes untrusted external data in the form of git commit messages and PR diffs to generate user-facing content.
Ingestion points: Data is ingested through the commits input field and the output of the git log command as specified in the Procedure section of SKILL.md.
Boundary markers: The instructions do not define boundary markers, delimiters (such as XML tags), or "ignore embedded instructions" warnings to separate untrusted commit messages from the agent's core instructions.
Capability inventory: The skill possesses the capability to execute shell commands (git log) and write data to the filesystem (walkthrough.md).
Sanitization: No sanitization or filtering logic is described to prevent malicious instructions embedded in a git commit message from influencing the LLM's output or downstream actions.

changelog-generator