The Agent Skills Directory

[COMMAND_EXECUTION]: The skill utilizes the GitHub CLI (gh) and git to perform repository management and monitoring tasks. These tools are used appropriately for the stated purpose of project management.
[PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection (Category 8) because it retrieves and analyzes content from external, potentially attacker-controlled sources like GitHub Issues, Pull Requests, and Git commit logs. • Ingestion points: gh issue list, gh pr list, and git log commands retrieve text into the agent's context. • Boundary markers: Absent; the skill does not instruct the agent to use delimiters or ignore embedded instructions within the ingested data. • Capability inventory: The agent has the capability to create issues, modify projects, and execute arbitrary GraphQL mutations via the gh api. • Sanitization: No evidence of content sanitization or escaping was found in the instructions.

project-management