story-type-analyzer
Pass
Audited by Gen Agent Trust Hub on Oct 22, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes user-provided story outlines and texts. Although an attacker could attempt to embed malicious instructions within a story summary to influence the agent's behavior, the skill does not have access to any dangerous tools (such as shell execution, network requests, or file writes) that could be leveraged for a security breach. The impact is limited to potentially influencing the analysis output itself.
- Ingestion points: User input via the prompt as defined in the '输入要求' section of
SKILL.md. - Boundary markers: The instructions do not explicitly specify the use of delimiters or 'ignore' instructions for the ingested story text.
- Capability inventory: The skill does not perform subprocess calls, network operations, or file-system modifications across its files.
- Sanitization: No input sanitization or validation logic is defined.
- [SAFE]: No other security concerns were identified. The skill's logic is purely instructional and focused on text summarization and classification.
Audit Metadata