The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted data from GitHub Pull Requests (titles, bodies, and code diffs) which could potentially contain malicious instructions intended to manipulate the agent's review logic.\n
Ingestion points: Content is retrieved via gh pr diff and gh pr view commands and by reading files from a local checkout as described in the Workflow section of SKILL.md.\n
Boundary markers: There are no explicit delimiters or instructions provided to the agent to treat PR data as untrusted or to ignore instructions embedded within the code or comments.\n
Capability inventory: The skill has permission to execute shell commands including gh, git, find, and grep, which provides a capability surface if the agent were to be misled by the input data.\n
Sanitization: No sanitization or validation steps are defined for the PR data before it is processed by the agent.

docs-check-kibana-oas