The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from GitHub pull requests, including descriptions and review findings, which could contain malicious instructions.
Ingestion points: Pull request content accessed via the prUrl parameter and the ship-pr tool loop in SKILL.md.
Boundary markers: None specified; the skill does not instruct the agent to use delimiters or ignore instructions embedded in the PR data.
Capability inventory: The skill allows for code pushing, merging, and execution of local scripts (SKILL.md).
Sanitization: No evidence of sanitization or validation of external input before processing.
[EXTERNAL_DOWNLOADS]: The skill uses npx to fetch and execute packages including @kodycodes/cli, @kentcdodds/ship-pr, and kcd-skills. These resources are associated with the identified author's ecosystem.
[COMMAND_EXECUTION]: The skill relies on shell command execution to perform its primary functions, such as running the kody CLI and local project tools for testing and merging.

ship-pr