ticket-authoring
Pass
Audited by Gen Agent Trust Hub on Oct 20, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and transform untrusted external content, such as Product Requirement Documents (PRDs), specifications, and bug reports, into structured tickets. It does not provide the agent with instructions to delimit this data or to ignore potential instructions embedded within the source material, creating a surface for indirect prompt injection.
- Ingestion points: The skill accepts "source material: a spec, a bug description, a request, or a conversation" (SKILL.md).
- Boundary markers: No explicit delimiters or instructions are provided to the agent to treat external content as passive data.
- Capability inventory: The skill is intended to write markdown files to the local file system (
tickets-[initiative].md) and interact with external issue trackers like Jira, Linear, or GitHub. - Sanitization: There are no instructions for validating, escaping, or filtering the input material before it is used to generate the ticket content.
Audit Metadata