dna-methylation-alignment-bismark

Pass

Audited by Gen Agent Trust Hub on Jun 16, 2026

Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill manages a bioinformatics pipeline by calling MCP tools for sequence alignment, BAM sorting, and indexing. These operations are performed using tool parameters derived from user-specified directories and files.
  • [PROMPT_INJECTION]: The skill includes an attack surface for indirect prompt injection as it processes external file names and user-provided paths (Step 1 and Step 2) to be used as tool arguments. This is an inherent risk of the bioinformatics domain, and the skill includes mitigation by requiring user validation for missing or ambiguous paths.
  • Ingestion points: FASTQ filenames via detect_fastq_samples and reference paths via prepare_bismark_genome (SKILL.md).
  • Boundary markers: Explicit delimiters for untrusted data are absent in the prompt interpolation logic.
  • Capability inventory: Subprocess execution for alignment, sorting, indexing, and directory creation across all mcp__bismark-tools calls (SKILL.md).
  • Sanitization: Path validation is explicitly mentioned in Step 2 for the Bismark genome folder.
  • [SAFE]: No obfuscation, persistence mechanisms, or unauthorized network operations were detected in the skill instructions or metadata.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 16, 2026, 12:17 PM
Security Audit — agent-trust-hub — dna-methylation-alignment-bismark