ticket-triage
Pass
Audited by Gen Agent Trust Hub on Sep 14, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and evaluate untrusted data in the form of development tickets (user stories, bug reports) provided via paste, file reading, or external trackers (Jira, Linear, GitHub).
- Ingestion points: Processes data from the prompt, local files, or external issue trackers referenced in
SKILL.mdunder the 'How to Get the Ticket' section. - Boundary markers: The skill lacks explicit instructions for the agent to use delimiters or 'ignore embedded instructions' prompts when interpolating ticket content into its evaluation logic.
- Capability inventory: The skill utilizes file reading and potentially MCP tools for Jira/Linear/GitHub. It does not perform arbitrary code execution or unauthorized network operations.
- Sanitization: There is no evidence of input validation or escaping for the external content before it is processed by the agent.
Audit Metadata