The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill ingests data from the user's project, such as commit messages and code diffs, to provide context for PR title generation. This content is technically untrusted and could be crafted to include malicious instructions to influence the agent.
Ingestion points: scripts/gather_context.py retrieves output from git log, git diff, and GitHub PR metadata.
Boundary markers: Data is passed to the agent as a structured JSON object, but the prompt lacks explicit instructions to ignore embedded commands within the diff or log content.
Capability inventory: The skill has the capability to write back to GitHub using gh pr edit in scripts/update_title.py.
Sanitization: No sanitization or filtering is performed on the data retrieved from the repository commands.
[COMMAND_EXECUTION]: The skill executes external CLI tools (git and gh) through Python's subprocess.run function. The implementation correctly uses list-based arguments and avoids shell=True, which is a secure practice that prevents standard command injection vulnerabilities when handling potentially variable input like the PR title.

pr-title