sentiment-analyzer
Pass
Audited by Gen Agent Trust Hub on Sep 15, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from user-supplied CSV files, which creates a surface for indirect prompt injection and stored XSS in output reports.\n
- Ingestion points: The
batchandreportcommands inscripts/main.py(lines 144 and 203) ingest content from CSV files provided as arguments.\n - Boundary markers: The skill does not use delimiters or boundary instructions to isolate input data from its analysis logic.\n
- Capability inventory:
scripts/main.pyperforms file-system read operations to load data and write operations to generate results in CSV and HTML formats.\n - Sanitization: There is no evidence of sanitization or escaping for the input text before it is analyzed by models or embedded into the HTML report template (line 261), which allows potentially malicious content to be preserved in the output.
Audit Metadata