set-jira-story-points
Pass
Audited by Gen Agent Trust Hub on May 6, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill processes user-supplied ticket data which constitutes an indirect prompt injection surface.
- Ingestion points: User-provided Jira keys and story point values (Step 1).
- Boundary markers: No delimiters or explicit instructions to ignore embedded commands are present in the workflow.
- Capability inventory: Modifies remote Jira tickets using the
editJiraIssuetool (Step 3). - Sanitization: Mitigates risk by enforcing strict regular expression matching for Jira keys (
^[A-Z]+-\d+$) and requiring story points to be positive integers. - [SAFE]: The skill attempts to retrieve a Jira Cloud ID from
~/.claude/CLAUDE.md. While this involves reading a file in the user directory, it is a standard platform configuration path and is used to establish environment context rather than extract sensitive credentials.
Audit Metadata