to-tickets
Pass
Audited by Gen Agent Trust Hub on Oct 1, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted external data by fetching bodies and comments from issue trackers and reference URLs.\n
- Ingestion points: Step 1 in
SKILL.mdindicates the agent will fetch and read the full body and comments of references, issue numbers, or URLs provided by the user.\n - Boundary markers: While the skill lacks explicit delimiters for external data, Step 4 requires the user to approve the ticket breakdown before execution, providing a manual safeguard.\n
- Capability inventory: The skill has the capability to write files to the local filesystem (under
.refinement/orbacklog/) and publish content to remote APIs for GitHub, GitLab, Jira, and Linear as described in Step 5.\n - Sanitization: There are no instructions to sanitize or validate the content retrieved from external sources before it is processed by the agent.
Audit Metadata