title-gen
Pass
Audited by Gen Agent Trust Hub on Sep 8, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill provides article title generation functionality. It does not contain any malicious code, command execution, or network communication patterns. It correctly limits its operations to text processing and reading a specific local configuration file.
- [INDIRECT_PROMPT_INJECTION]: The skill processes user-provided article content which acts as an untrusted input surface.
- Ingestion points: Article content or core viewpoints provided by the user at runtime in SKILL.md.
- Boundary markers: Absent.
- Capability inventory: Text generation only. The skill instructions do not invoke shell commands, file system writes, or network tools.
- Sanitization: Absent. Given the skill lacks the ability to perform high-risk actions, the processing of external content for title generation is considered safe.
Audit Metadata