deeptools

Pass

Audited by Gen Agent Trust Hub on Jun 27, 2026

Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill utilizes helper scripts like scripts/workflow_generator.py to create bash scripts which are then executed with chmod +x and direct invocation. This is a standard automation pattern for bioinformatics tools to manage multi-step analysis pipelines.
  • [DYNAMIC_EXECUTION]: The scripts/workflow_generator.py script dynamically assembles executable shell scripts from internal templates based on user parameters. This is used to facilitate the creation of complex deepTools commands for the user.
  • [INDIRECT_PROMPT_INJECTION]: The scripts/workflow_generator.py script takes parameters such as file paths and threads and interpolates them into bash script templates. While this represents a potential injection surface if malicious strings are provided as filenames, the risk is mitigated by the local nature of the execution and the specific use case for genomic data processing.
  • Ingestion points: Command-line arguments to scripts/workflow_generator.py.
  • Boundary markers: Absent in the generated shell script templates.
  • Capability inventory: Shell command execution and execution of generated scripts via SKILL.md instructions.
  • Sanitization: None detected in the template interpolation logic.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 27, 2026, 11:42 AM
Security Audit — agent-trust-hub — deeptools