The Agent Skills Directory

[CREDENTIALS_UNSAFE]: The skill reads the Jira CLI configuration file at ~/.config/.jira/.config.yml to extract project information. This file typically contains sensitive authentication tokens or API keys, and direct file access by the agent poses a risk of credential exposure.
[PROMPT_INJECTION]: The skill processes Jira ticket summaries and descriptions to prioritize tasks, creating a surface for indirect prompt injection. Malicious instructions embedded in a ticket could attempt to influence the agent's decision-making or behavior.
Ingestion points: External ticket data retrieved via jira issue list.
Boundary markers: No delimiters or specific instructions are provided to the model to ignore potential injections within ticket content.
Capability inventory: The skill has the ability to execute shell commands and interact with the Jira CLI.
Sanitization: No content validation or sanitization is performed on the ingested ticket data.
[COMMAND_EXECUTION]: The skill executes multiple shell commands, including cat, grep, and awk, as well as several jira CLI commands to manage and analyze project data.

jira-todo