foundations-consumer-neuroscience

Pass

Audited by Gen Agent Trust Hub on Oct 17, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONDYNAMIC_EXECUTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and evaluate external neuromarketing studies, vendor reports, and biometric data, creating an attack surface for indirect prompt injection.
  • Ingestion points: Evaluation of neuromarketing studies, vendor pitches, and lab findings (fixation heatmaps, GSR spikes) as described in SKILL.md.
  • Boundary markers: The skill does not define specific delimiters or instructions to ignore embedded commands in the analyzed reports.
  • Capability inventory: The agent is instructed to execute the append_learning.py script to modify local files.
  • Sanitization: No sanitization or filtering logic is specified for the external data being processed.
  • [DYNAMIC_EXECUTION]: The skill instructs the agent to execute a script (agents-skills-feedback-loop/scripts/append_learning.py) to log observations and updates into learnings.md.
  • Evidence: The 'Learnings Loop' section in SKILL.md explicitly directs the agent to run the script using shell commands to modify skill data.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 17, 2026, 08:31 AM