matt-to-tickets
Pass
Audited by Gen Agent Trust Hub on Oct 15, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes data from external sources such as specification documents, issue tracker URLs, and codebase files to generate ticket content. This ingestion of external, potentially untrusted data constitutes an indirect prompt injection surface where instructions hidden in those documents could influence the output.
- Ingestion points: As described in
SKILL.md, the agent fetches content from user-provided spec paths, issue URLs, and explores the codebase to gather context. - Boundary markers: There are no defined delimiters or specific instructions for the agent to ignore executable-style text or embedded directives found within the external documents it reads.
- Capability inventory: The skill utilizes file system access to write markdown files to the
.scratch/directory and interacts with external issue tracking APIs (GitHub, Linear) to publish generated tickets. - Sanitization: The skill instructions do not specify any validation or sanitization steps for the data fetched from external references prior to processing.
Audit Metadata