scientific-critical-thinking

Pass

Audited by Gen Agent Trust Hub on Aug 1, 2026

Risk Level: SAFECOMMAND_EXECUTIONDATA_EXFILTRATIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill instructs the agent to execute a local script scripts/generate_schematic.py to produce diagrams. The command python scripts/generate_schematic.py "your diagram description" -o figures/output.png incorporates user-supplied natural language descriptions, which is a standard functional pattern for this agent's workflow.
  • [DATA_EXFILTRATION]: The skill references an external repository https://github.com/aipoch/medical-research-skills as its source. This is a legitimate reference to the author's public repository and does not involve the exfiltration of sensitive user data.
  • [PROMPT_INJECTION]: The skill exhibits a surface for indirect prompt injection. 1. Ingestion points: scientific papers and claims processed in SKILL.md. 2. Boundary markers: None identified. 3. Capability inventory: Local file system read/write via figures/ directory and shell command execution via scripts/generate_schematic.py. 4. Sanitization: No explicit sanitization or filtering of input data is described.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 1, 2026, 10:43 AM
Security Audit — agent-trust-hub — scientific-critical-thinking