The Agent Skills Directory

[COMMAND_EXECUTION]: The skill utilizes the gh and git command-line interfaces to retrieve repository information. Its operations are restricted to read-only actions (GET requests and view commands), which is a security best practice for automated triage tools.
[PROMPT_INJECTION]: The skill possesses an indirect prompt injection attack surface because it processes untrusted content from GitHub issues and pull requests. This is a characteristic of the skill's core purpose of analysis.
Ingestion points: External data is ingested from GitHub issues and pull requests via gh view commands in SKILL.md.
Boundary markers: No explicit delimiters or boundary instructions are provided to the agent to distinguish between repository data and system instructions.
Capability inventory: The skill executes shell commands (gh, git) and performs local file system writes to the /tmp directory as specified in SKILL.md.
Sanitization: There is no documented evidence of sanitization or filtering of the content retrieved from GitHub before it is analyzed by the agent.

shen-shi