agent-test-long-runner
Pass
Audited by Gen Agent Trust Hub on Mar 1, 2026
Risk Level: SAFEPROMPT_INJECTIONNO_CODE
Full Analysis
- [PROMPT_INJECTION]: The skill is designed to ingest and analyze untrusted external data (e.g., codebases, research sources), creating a surface for indirect prompt injection.
- Ingestion points: External documentation, codebases, and research sources.
- Boundary markers: Absent; there are no delimiters or instructions to ignore embedded commands in the processed data.
- Capability inventory: No file-system, network, or execution capabilities are defined in the provided markdown file.
- Sanitization: Absent; no validation or filtering of external content is specified.
- [NO_CODE]: The skill contains only natural language instructions and no executable scripts, shell commands, or binary files.
Audit Metadata