openspec-to-tickets
Pass
Audited by Gen Agent Trust Hub on Nov 11, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTIONEXTERNAL_DOWNLOADS
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill reads and processes markdown files from the
openspec/changes/directory to define ticket requirements and vertical slices. This creates an attack surface where malicious content within a specification file could attempt to influence the agent's logic during the ticket drafting phase. - Ingestion points:
proposal.md,design.md,specs/, andtasks.mdwithin theopenspec/changes/folder. - Boundary markers: The instructions do not specify the use of delimiters or instructions to ignore embedded commands for the parsed content.
- Capability inventory: File system access to write
tickets.mdandAGENTS.md, and shell execution foropenspec,gh, andjira-clicommands. - Sanitization: No specific sanitization or validation of the input markdown content is mentioned prior to its use in ticket generation.
- [COMMAND_EXECUTION]: The skill makes extensive use of command-line interfaces (
openspec,gh,jira-cli) to validate specifications and publish tickets to external trackers. These operations involve executing shell commands with arguments derived from the repository structure and user-provided inputs. - [EXTERNAL_DOWNLOADS]: The skill's documentation points to external GitHub repositories for its own installation (
agoodway/GoodSkills) and for project dependencies such as the Jira CLI. These resources are from established sources and are expected for the skill's functionality.
Audit Metadata