run-ai-checks
Pass
Audited by Gen Agent Trust Hub on Jun 16, 2026
Risk Level: SAFE
Full Analysis
- [COMMAND_EXECUTION]: The skill executes local Python scripts including
data-check.py,pytest, and a documentation generator located in a sibling vendor directory (../BBMRI-ERIC-Directory-Data-Manager-Manual/scripts/generate_checks_docs.py). These executions are part of a standard validation and testing workflow for the project. - [DATA_EXPOSURE]: Accesses project-specific directories such as
checks/,ai-check-cache/, andtests/. It processes biological directory metadata (narratives and structured data) to identify gaps. No sensitive system files or credentials are targeted. - [INDIRECT_PROMPT_INJECTION]: The skill's primary function involves analyzing untrusted narrative descriptions from external directory snapshots. This presents an attack surface where an attacker could embed malicious instructions in the data being reviewed. The skill mitigates this by requiring a multi-step validation process, including checksum verification and a clean-load requirement before results are committed to the cache.
Audit Metadata