The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill processes untrusted Pull Request content which may contain instructions that could attempt to influence the agent's behavior during the landing process.
Ingestion points: Data from GitHub Pull Requests (titles, descriptions, and comments) for the openclaw/openclaw repository.
Boundary markers: There are no explicit delimiters or instructions provided to the agent to disregard instructions embedded within the PR content.
Capability inventory: The skill is designed to perform rebase, force-push, and merge git operations.
Sanitization: The provided instructions do not specify any sanitization, filtering, or validation of the ingested PR content before it is processed.

landpr