The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data in the form of Git commit messages retrieved via git log. These messages, which can be authored by any contributor to the repository, could contain malicious instructions designed to manipulate the agent's output or behavior during the changelog generation process.
Ingestion points: Commit history retrieved through git log in Step 2 of the workflow.
Boundary markers: The skill does not define explicit delimiters or instructions to ignore potential commands embedded within the commit messages it processes.
Capability inventory: The skill has the ability to execute git shell commands and perform file write operations to CHANGELOG.md and website/src/pages/changelog.md.
Sanitization: No explicit sanitization or filtering is performed on the commit message content to strip potential prompt injection sequences.
[COMMAND_EXECUTION]: The skill utilizes local shell commands to interact with the repository's version control system.
Evidence: The workflow includes calls to git describe, git log, and git config. These are standard tools for a changelog generation skill, but they represent a command execution surface that relies on the local environment's configuration.

skillshare-changelog