setting-up-regression-runs
Pass
Audited by Gen Agent Trust Hub on Oct 30, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill follows secure practices by limiting its operations to reading local configuration files and invoking a specific, authorized internal tool for test run creation. No malicious code, obfuscation, or unauthorized data access patterns were detected.
- [INDIRECT_PROMPT_INJECTION]: The skill has a standard attack surface where it ingests user-supplied strings (milestone names and spec exclusions) and interpolates them into arguments for another tool.
- Ingestion points: User input for profile selection, milestone naming, and spec exclusions defined in
SKILL.md. - Boundary markers: None explicitly defined in the prompt interpolation logic.
- Capability inventory: The skill is restricted to
Readoperations and calling the specificSkill(bitwarden-testmo-tools:creating-test-runs). It does not possess capabilities for arbitrary command execution, file writing, or network access. - Sanitization: No specific sanitization logic is implemented for user-provided milestone names.
Audit Metadata