Skills
Navigate
skills/azanir/qa-skills/qa-test-reporter/Gen Agent Trust Hub

qa-test-reporter

Pass

Audited by Gen Agent Trust Hub on Sep 18, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted external data from test reports and CI logs, which could contain malicious instructions designed to influence the agent's go/no-go recommendations.
  • Ingestion points: SKILL.md and references/report-formats.md specify parsing JUnit XML, Allure JSON, and GitHub Actions logs from local paths or remote URLs.
  • Boundary markers: The instructions lack explicit boundary markers or directives for the agent to ignore instructions embedded within the processed test data.
  • Capability inventory: The skill uses Memory MCP to persist trends and GitHub MCP to fetch external artifacts. Its primary output is a go/no-go recommendation used for release decisions.
  • Sanitization: No sanitization or validation of the content within test names, suite names, or failure messages is specified.
  • [EXTERNAL_DOWNLOADS]: The skill fetches test artifacts and CI logs from GitHub Actions workflow runs for analysis.
  • Evidence: SKILL.md and references/report-formats.md describe using the GitHub MCP to retrieve artifacts and logs from workflow runs.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 18, 2026, 05:38 PM
Security Audit — agent-trust-hub — qa-test-reporter