The Agent Skills Directory

[COMMAND_EXECUTION]: The skill's primary operation involves executing shell commands to interact with the local repository and GitHub. It uses gh pr checkout to switch branches, gh pr view to fetch JSON metadata for pull requests, and git diff to identify changes in the CHANGELOG.md file. It also leverages standard Unix utilities such as awk, sed, nl, and rg for text extraction and line numbering.
[INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data which could theoretically be used to influence the agent's behavior.
Ingestion points: The skill reads PR titles and descriptions from GitHub via gh and consumes the contents of the local CHANGELOG.md file, both of which are controlled by external contributors.
Boundary markers: The agent is not provided with specific delimiters or instructions to treat the ingested text as data rather than instructions.
Capability inventory: The agent has the ability to execute shell commands, access the network via the GitHub CLI, and read files within the repository scope.
Sanitization: There is no explicit sanitization step for the PR metadata or changelog text before it is analyzed by the agent.

otel-changelog-pr-verifier