parable
Pass
Audited by Gen Agent Trust Hub on Sep 16, 2026
Risk Level: SAFEPROMPT_INJECTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill files contain prompt templates and metadata configuration with no executable scripts, sensitive data access, or network calls.
- [PROMPT_INJECTION]: The skill uses strict instructional language to ensure the agent follows the specific fable-writing format. These instructions are standard for prompt engineering and do not attempt to bypass safety filters or exfiltrate data.
- [INDIRECT_PROMPT_INJECTION]: The skill processes user-provided concepts at the '{concept}' placeholder in SKILL.md. While it lacks explicit boundary markers or sanitization, there are no dangerous tool capabilities (like file system or network access) that could be exploited, and the risk is mitigated by standard agent safety protocols.
Audit Metadata