spiral-curriculum

Pass

Audited by Gen Agent Trust Hub on Aug 31, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill processes data from existing classroom content to maintain conceptual memory and progress the curriculum.
  • Ingestion points: The skill uses read_stage_outline and read_stage in SKILL.md to retrieve previously generated content.
  • Boundary markers: There are no explicit instructions or delimiters defined to prevent the agent from following instructions embedded within the retrieved classroom content.
  • Capability inventory: The skill has the ability to create folders (create_folder), generate scenes (generate_scene), modify stage actions (generate_actions), and generate audio (generate_tts).
  • Sanitization: The instructions do not specify any sanitization or validation logic for the content read from previous stages before it is used to influence the generation of subsequent scenes.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 31, 2026, 10:40 AM
Security Audit — agent-trust-hub — spiral-curriculum