bio-data-visualization-lollipop-protein-maps
Pass
Audited by Gen Agent Trust Hub on Oct 8, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process external Mutation Annotation Format (MAF) files, creating a surface for potential indirect prompt injection attacks where malicious data could influence agent output.
- Ingestion points: External data is loaded from 'cohort.maf' in SKILL.md and examples/lollipop_phd.R.
- Boundary markers: The instructions do not define boundary markers or provide warnings to the agent regarding potential embedded instructions in the data files.
- Capability inventory: The skill uses R scripts to read files, perform data transformations via regex, and generate PDF/HTML output files.
- Sanitization: There is no evidence of input validation or sanitization for the mutation metadata before processing.
Audit Metadata