batch-processing
Pass
Audited by Gen Agent Trust Hub on Feb 17, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- Indirect Prompt Injection (LOW): The skill demonstrates a workflow that ingests external documents from the file system and interpolates them directly into prompts. This creates a surface where malicious instructions in the data could be executed by the agent.
- Ingestion points: The skill loads data from
data/*.txtin the use-case examples. - Boundary markers: No delimiters or warning instructions are used to separate user data from system prompts.
- Capability inventory: The skill utilizes the
anthropiclibrary for network communication and has local file write permissions for creating JSONL batches. - Sanitization: There is no evidence of input validation or content filtering before the data is processed.
Audit Metadata