analysis-api-create-cherry-pick-issue
Pass
Audited by Gen Agent Trust Hub on Oct 8, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill possesses an attack surface for indirect prompt injection because it ingests data from external sources to perform automated tasks.
- Ingestion points: The skill fetches the
summaryandSeverityfrom an existing YouTrack issue viamcp__YouTrack__get_issue(SKILL.md, Step 1). - Boundary markers: The skill uses a structured template for the summary and description, which helps delimit external content.
- Capability inventory: The skill uses
mcp__YouTrack__create_issue,mcp__YouTrack__manage_issue_tags, andmcp__YouTrack__link_issuesto perform write operations in the tracking system. - Sanitization: The workflow incorporates a human review step (Step 2: Confirm with user) requiring the user to verify the resolved summary, priority, and assignee before any write operations occur, significantly mitigating the risk of executing malicious instructions embedded in the original issue data.
Audit Metadata