The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill defines a workflow for processing user-supplied financial data, which creates a potential surface for indirect prompt injection. However, no malicious content was found. Ingestion points: Financial parameters defined in SKILL.md, such as 'underlying_exposure' and 'futures_contract'. Boundary markers: The skill does not implement explicit delimiters or boundary markers for ingested data. Capability inventory: Analysis is limited to reasoning and calculations; the validation script (scripts/check_test_cases.py) is restricted to local file reading with no network or write access. Sanitization: The workflow relies on the agent's reasoning capabilities rather than programmatic input validation.
[SAFE]: No malicious patterns, obfuscation, unauthorized exfiltration, or persistence mechanisms were found across the skill's instructions, metadata, or scripts. The project status is correctly identified as a community project, and all external links point to the vendor's official resources.

futures-hedgecraft