Run triage duty for CET/Cloud, Server, or Drivers/DBX. Retrieves Needs Triage tickets from Jira, builds a triage plan, and applies changes after human confirmation.
74
68%
Does it follow best practices?
Impact
79%
2.07xAverage score across 3 eval scenarios
Low
Low-risk findings worth noting
Fix and improve this skill with Tessl
tessl review fix ./.claude/skills/triage/SKILL.mdLow
Low-risk findings.
2 low severity findings. Worth noting, but not necessarily harmful.
The skill exposes the agent to untrusted, user-generated content from public third-party sources, creating a risk of indirect prompt injection. This includes browsing arbitrary URLs, reading social media posts or forum comments, and analyzing content from unknown websites.
The required workflow reads Jira tickets and their free-text fields (summary/description/comments and one-level direct links) via the `jira` tool in Steps 2 and 6 (JQL queries selecting DOCSP tickets in “Needs Triage” and then fetching full ticket details for analysis).
The skill fetches instructions or code from an external URL at runtime, and the fetched content directly controls the agent’s prompts or executes code. This dynamic dependency allows the external source to modify the agent’s behavior without any changes to the skill itself.
The skill explicitly fetches internal wiki and Google Sheet URLs at runtime (e.g., https://wiki.corp.mongodb.com/pages/viewpage.action?pageId=560136334) via the glean_mcp/Atlassian MCP to load routing rules, component-owner mappings, label criteria, and embargo lists that directly control triage decisions and agent behavior.
d9cb237
If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.