The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill reads external data that could contain malicious instructions designed to influence the agent's actions.
Ingestion points: Data is ingested from issue trackers using gh issue view and jira issue view in Phase 1, and web results using Context7/web for Agent 3.
Boundary markers: The instructions do not specify the use of delimiters or explicit warnings to ignore instructions embedded in the retrieved content.
Capability inventory: The skill uses Bash, Edit, Write, and TaskCreate tools across the project environment as defined in SKILL.md.
Sanitization: No sanitization or safety checks are performed on the retrieved text content before it is processed by the AI.
[COMMAND_EXECUTION]: To achieve its goals, the skill uses the Bash tool to discover project workflows, run linting, and execute test suites via npm, make, or other task runners.
[EXTERNAL_DOWNLOADS]: The skill interacts with external services to view issues and search the web using the WebFetch tool and platform-specific CLIs.

fix-bug