memory-parable

Pass

Audited by Gen Agent Trust Hub on Sep 3, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill processes user-supplied data to define the 'Domain' for generating educational content, which creates a standard attack surface for indirect instructions.
  • Ingestion points: The Domain: [your field] parameter in SKILL.md accepts arbitrary user input.
  • Boundary markers: The skill lacks explicit boundary delimiters or instructions to ignore potential commands embedded within the user-provided domain string.
  • Capability inventory: The skill has no capabilities involving file system writes, network requests, or command execution; it is restricted to text generation.
  • Sanitization: There is no evidence of input validation or sanitization for the user-supplied domain field.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 3, 2026, 10:29 AM
Security Audit — agent-trust-hub — memory-parable