The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted data from external sources that could contain malicious instructions.
Ingestion points: Reads ticket summaries, descriptions, and comments via jira issue list commands in Phase 3.
Boundary markers: The skill lacks explicit boundary markers or 'ignore' instructions when interpolating ticket content into the final report templates.
Capability inventory: The skill has access to shell commands (jira, git, cat, date) and file system tools (Read, TodoWrite).
Sanitization: There is no evidence of sanitization or escaping of the content retrieved from Jira before it is processed by the agent.
[COMMAND_EXECUTION]: The skill executes multiple shell commands to gather data.
Evidence: Uses cat ~/.config/.jira/.config.yml to read local configuration and grep/awk to parse it. It also executes jira and git commands based on derived arguments.

jira-daily