testcase-grill
Pass
Audited by Gen Agent Trust Hub on Sep 13, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONNO_CODE
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes data from a 'page or block' to generate output, which is a potential surface for indirect prompt injection where malicious instructions in the input could influence the agent.
- Ingestion points: Data is ingested through the prompt context as defined in agents/openai.yaml.
- Boundary markers: There are no explicit delimiters or instructions to ignore embedded commands in the input data.
- Capability inventory: The analyzed files contain no scripts, network calls, or file system operations.
- Sanitization: No input validation or sanitization routines are defined in the skill configuration.
- [NO_CODE]: This skill consists entirely of metadata and instructional text without any executable scripts or binary files.
Audit Metadata