ticket-and-pr-prose
Pass
Audited by Gen Agent Trust Hub on Jul 26, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill defines a documentation format and process. No malicious patterns, obfuscation, or unauthorized data access were detected.- [COMMAND_EXECUTION]: The skill instructs the agent to use standard tools like the GitHub CLI (
gh) and the Linear MCP to publish documentation. The recommended use of--body-filefor the GitHub CLI is a security best practice that prevents shell interpretation issues when handling complex Markdown content.- [PROMPT_INJECTION]: The skill processes project source code and git diffs, creating a surface for potential indirect prompt injection. Ingestion points: Source code and git diff output as described in the 'Method' section. Boundary markers: Absent; the skill does not specify delimiters to separate untrusted code content from instructions. Capability inventory: Includes the ability to write to external services via the Linear MCP (save_issue) and GitHub CLI (gh pr create/edit). Sanitization: Absent; the skill relies on the agent to interpret the data directly without a pre-processing validation step. This risk is considered inherent to the skill's primary purpose of documenting code changes.
Audit Metadata