momentic-result-classification
Pass
Audited by Gen Agent Trust Hub on Apr 8, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill processes data from external applications through test results, which is a vector for indirect prompt injection.
- Ingestion points: The skill reads contents from
metadata.json,console.json,har-pages.log,har-entries.log, and HTML/DOM snapshots (<snapshotId>.html) located in thetest-results/or.momentic-mcp/directories. - Boundary markers: Absent. There are no instructions or delimiters provided to the agent to distinguish between the skill's instructions and the potentially untrusted content of the test logs or snapshots.
- Capability inventory: The agent uses
momentic_list_runsandmomentic_get_runtools to retrieve and analyze run data. - Sanitization: Absent. The skill does not define any validation or filtering mechanisms for the data retrieved from the test results before processing.
Audit Metadata