The Agent Skills Directory

[COMMAND_EXECUTION]: The skill provides instructions for the agent to execute shell commands using the GitHub CLI (gh) to edit pull requests and attach media files, as seen in references/media.md. It also specifies the use of a specialized tool named pr-readiness check to validate observations within the PR body in SKILL.md.
[INDIRECT_PROMPT_INJECTION]: The skill possesses a surface for indirect prompt injection as it is designed to ingest and summarize untrusted data from the repository environment.
Ingestion points: The agent is instructed to read and summarize repository source code, diffs, and test execution outputs to populate the 'Summary' and 'Evidence' sections of the PR.
Boundary markers: While the skill uses a structured Markdown template, it does not include explicit instructions or markers to disregard potentially malicious instructions embedded within the ingested code or test data.
Capability inventory: The agent has the capability to execute shell commands (gh CLI) and file operations as described in the PR creation and media upload workflows.
Sanitization: There is no mention of sanitization, filtering, or validation for the content retrieved from the repository before it is interpolated into the PR template.

pr