headline-four-functions
Pass
Audited by Gen Agent Trust Hub on Oct 7, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill contains markdown-based instructions and pedagogical frameworks for analyzing marketing copy. It does not include scripts, binaries, or remote dependencies.
- [INDIRECT_PROMPT_INJECTION]: The skill's primary function is to ingest untrusted user data (advertisement headlines) for evaluation.
- Ingestion points: User input prompts identified in SKILL.md under the '触发场景' (Trigger Scenarios) section.
- Boundary markers: None explicitly defined in the instructions for separating user input from analysis logic.
- Capability inventory: The skill has no identified capabilities; it performs no subprocess calls, file writes, or network operations.
- Sanitization: None present. However, given the lack of executable capabilities, the surface for instruction-based exploitation is negligible.
Audit Metadata