crypto-market-neutral
Pass
Audited by Gen Agent Trust Hub on Apr 25, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill processes untrusted CSV data which constitutes an indirect prompt injection surface.\n
- Ingestion points: The
scripts/crypto_market_neutral_diagnostics.pyscript reads from a user-provided CSV file.\n - Boundary markers: There are no explicit instructions or delimiters used to warn the agent about potentially malicious instructions embedded in the CSV data.\n
- Capability inventory: The skill performs file system read and write operations via the provided Python script and provides the summarized results to the agent context.\n
- Sanitization: While the script converts data to numeric and datetime formats, it does not sanitize the text content against adversarial instructions intended to influence the agent.
Audit Metadata