The Agent Skills Directory

[PROMPT_INJECTION]: The skill processes untrusted content from GitHub issues, creating a surface for indirect prompt injection.
Ingestion points: External data enters the agent context through the github_get_issue tool, which reads issue titles, descriptions, and comments.
Boundary markers: The workflow lacks instructions to wrap issue content in delimiters or to explicitly ignore embedded instructions during the analysis process.
Capability inventory: The agent has the ability to read and write local files, perform repository searches with grep, and use various GitHub API tools.
Sanitization: No sanitization, validation, or filtering of the external issue content is specified before the analysis phase.
[DATA_EXFILTRATION]: The skill performs search operations and gathers references from GitHub and established documentation platforms. These network activities are essential for the skill's operation and target well-known, trusted services.
[COMMAND_EXECUTION]: The skill and its reference documentation recommend using local shell-based tools like grep and git log to perform static and historical analysis of the codebase, which is a routine and safe part of software troubleshooting.

github-issue-rca