report-analyzer-issue
Pass
Audited by Gen Agent Trust Hub on Jul 3, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill uses the GitHub CLI (
gh) to create issues on theseqra/opentaintrepository. It constructs the command using user-provided strings for the issue title and body file path. - [PROMPT_INJECTION]: The skill ingests diagnostic data and test results to generate reports, which creates a surface for indirect prompt injection where malicious content in the inputs could attempt to influence agent behavior. 1. Ingestion points: Diagnosis input and test-result.json files. 2. Boundary markers: None present. 3. Capability inventory: Local file system writes and shell command execution via
gh. 4. Sanitization: No validation or sanitization of ingested diagnostic content is specified.
Audit Metadata