pr-ruancat-repo
Pass
Audited by Gen Agent Trust Hub on Sep 29, 2026
Risk Level: SAFECOMMAND_EXECUTIONDYNAMIC_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill automates repository operations by generating and executing shell commands using 'git' and the GitHub CLI ('gh'). The execution is performed locally via 'node:child_process.execSync' within a user-approved workflow.
- [DYNAMIC_EXECUTION]: In 'Script Automation Mode', the agent generates a custom TypeScript script ('batch-pr.ts') and configuration files in a timestamped local directory, instructing the user to execute the script using 'npx tsx'.
- [INDIRECT_PROMPT_INJECTION]: The skill processes repository content to perform automated modifications, presenting an indirect prompt injection surface. Evidence Chain: 1. Ingestion points: Local files matched by glob patterns defined in 'pr-config.json'. 2. Boundary markers: The 'spec.md' and 'pr-transform.json' files provide explicit definitions of the intended transformations for user review. 3. Capability inventory: Use of 'execSync' for git operations and 'fs.writeFileSync' for file modifications. 4. Sanitization: The script uses file-based inputs for PR bodies and escapes quotes in PR titles to mitigate shell injection risks.
Audit Metadata