meta-picos-generator
Pass
Audited by Gen Agent Trust Hub on Aug 1, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: No malicious patterns, obfuscation, or unauthorized data access were detected. The skill is scoped to clinical research data extraction.- [EXTERNAL_DOWNLOADS]: The skill references the author's repository at github.com/aipoch/medical-research-skills. This is a vendor-owned resource used for sourcing documentation and does not involve untrusted remote execution or unauthorized external communication.- [COMMAND_EXECUTION]: Includes a local validation script at scripts/validate_skill.py. Analysis of the Python source code confirms it is a minimal helper script using argparse for environmental checks; it does not perform network operations or access sensitive file paths.- [PROMPT_INJECTION]: The instructions guide the agent to clean user-provided titles and extract information into a strict JSON schema. These structured requirements and the specific text-cleaning step mitigate the risk of indirect prompt injection from processed data.
Audit Metadata