cross-venue-crypto-mm
Pass
Audited by Gen Agent Trust Hub on Apr 25, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill uses
pythonto execute a diagnostic script (scripts/cross_venue_crypto_mm_diagnostics.py). This is the primary intended behavior for generating market diagnostics from input data. - [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection through its ingestion of untrusted data.
- Ingestion points: Data is ingested from
input.csvvia the diagnostic script. - Boundary markers: The agent lacks explicit instructions to treat the diagnostic output as untrusted or to ignore embedded instructions.
- Capability inventory: The skill can execute local scripts and write files to the filesystem.
- Sanitization: While the script coerces data values to numeric types, it includes user-provided column names directly in the JSON output, which could be used to inject instructions.
Audit Metadata