qa-metrics
Pass
Audited by Gen Agent Trust Hub on Sep 15, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill establishes a workflow where the agent ingests and processes data from external systems, including CI providers (GitHub Actions, GitLab CI, Jenkins, Buildkite) and issue trackers (Jira, Linear, GitHub Issues). This creates a vulnerability surface where malicious content stored in these external systems—such as bug descriptions, commit messages, or test failure logs—could potentially influence the agent's behavior.
- Ingestion points: CI system APIs (run results, duration, flakiness), issue tracker APIs (labels, severity, MTTR), and test runner output files (JUnit XML, coverage JSON/LCOV).
- Boundary markers: The skill does not provide specific instructions or delimiters to isolate untrusted external data from the agent's internal instruction set.
- Capability inventory: The skill instructions involve reading from external APIs, analyzing local files, and reporting findings to stakeholders via dashboards.
- Sanitization: There are no explicit requirements for sanitizing, escaping, or validating external content before the agent processes it for analysis.
Audit Metadata