momentic-result-classification
Pass
Audited by Gen Agent Trust Hub on May 22, 2026
Risk Level: SAFE
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes potentially untrusted data from test run results, including application logs, console output, and network (HAR) entries. This creates an indirect prompt injection surface where a malicious application under test could attempt to influence the agent's behavior.
- Ingestion points: Data enters via momentic_get_run, momentic_get_step_result, and momentic_get_test_steps_for_run (SKILL.md).
- Boundary markers: No specific boundary markers or instructions to ignore embedded content are present.
- Capability inventory: No high-risk capabilities such as arbitrary command execution or external network access are present in this skill.
- Sanitization: No sanitization of the processed test data is described.
Audit Metadata