literature-filtering
Pass
Audited by Gen Agent Trust Hub on Aug 1, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill processes untrusted external data (literature titles and abstracts) supplied via CSV files.
- Ingestion points: Literature records are ingested from 'input_literature.csv' into the agent's context.
- Boundary markers: No delimiters or instructions are provided to the agent to treat the record content as data rather than instructions.
- Capability inventory: The skill performs local file read/write operations and console logging.
- Sanitization: No sanitization or escaping of external literature content is implemented before it is processed or logged, which could allow instructions embedded in titles or abstracts to influence the agent.
Audit Metadata