study-strategy-selector

Pass

Audited by Gen Agent Trust Hub on Jun 13, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill performs as described, providing study recommendations based on academic research (Dunlosky et al., 2013). No malicious intent was detected.
  • [NO_CODE]: This skill consists entirely of configuration and instructional prompts. It does not include any scripts, executables, or third-party library dependencies.
  • [DATA_EXPOSURE]: There are no patterns suggesting access to sensitive files (e.g., credentials, SSH keys) or environment variables.
  • [PROMPT_INJECTION]: The prompt instructions are focused on educational content and do not attempt to bypass safety filters, extract system prompts, or override the agent's core instructions.
  • [INDIRECT_PROMPT_INJECTION]: While the skill ingests user-provided data such as 'learning_task' and 'student_profiles' without explicit boundary markers, the skill's capabilities are limited to text generation. It lacks access to dangerous tools (file system, network, shell), rendering the impact of potential data-driven instruction overrides negligible.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 13, 2026, 07:23 AM
Security Audit — agent-trust-hub — study-strategy-selector