depmap

Pass

Audited by Gen Agent Trust Hub on Oct 1, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill fetches genomic datasets and metadata from the DepMap portal (depmap.org) and Figshare (figshare.com). These are recognized and reputable scientific data repositories.\n- [INDIRECT_PROMPT_INJECTION]: The skill processes external API responses and CSV files, creating a potential surface for indirect prompt injection.\n
  • Ingestion points: Data is retrieved through API calls in the depmap_get and get_gene_dependency functions, and via file reading in load_depmap_gene_effect (SKILL.md) and load_prism_data (dependency_analysis.md).\n
  • Boundary markers: The skill does not implement delimiters or explicit instructions to ignore potentially malicious embedded content within the ingested datasets.\n
  • Capability inventory: The skill utilizes network access via the requests library and file system operations via pandas and built-in open() functions.\n
  • Sanitization: There is no evidence of data sanitization, filtering, or validation performed on external content prior to analysis.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 1, 2026, 07:50 AM
Security Audit — agent-trust-hub — depmap