The Agent Skills Directory

[COMMAND_EXECUTION]: The skill uses the Bash tool to execute jira and git commands (e.g., jira me, jira issue list, git branch). It also reads the local Jira configuration file located at ~/.config/.jira/.config.yml to extract project settings, which is standard for the tool's primary purpose.\n- [INDIRECT_PROMPT_INJECTION]: The skill processes external data from Jira ticket summaries, descriptions, and comments, which constitutes a potential attack surface.\n
Ingestion points: External data is ingested through the standard output of jira issue list commands in Phase 3.\n
Boundary markers: No explicit boundary markers or instructions to ignore embedded commands are present in the processing logic.\n
Capability inventory: The skill has access to Bash, Read, Task, and TodoWrite tools, enabling file system interaction and command execution.\n
Sanitization: The skill does not explicitly sanitize or escape ticket content before including it in the generated report, which could allow malicious content in a Jira ticket to influence the agent's behavior at runtime.\n- [DYNAMIC_EXECUTION]: The evaluation scenarios in evals/evals.json involve instructions for the agent to create executable mock scripts and modify the system PATH to simulate the environment during testing.

jira-todo