content-topic-generator
Pass
Audited by Gen Agent Trust Hub on Apr 5, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill is strictly instructional and serves as a content creation assistant. It does not include any executable scripts, binary files, or system-level configuration changes.
- [SAFE]: Analysis of all files confirmed no network operations (curl, wget, fetch), no sensitive file path access (SSH, environment variables, credentials), and no hardcoded secrets.
- [PROMPT_INJECTION]: The skill features a surface for indirect prompt injection as it processes untrusted user-provided content (articles/tweets) to generate new topics.
- Ingestion points: Workflow Step 1 in
SKILL.mdreads user-supplied content. - Boundary markers: Absent.
- Capability inventory: No tools for network, shell, or file system access are provided or requested.
- Sanitization: Absent. Despite the lack of boundary markers, the risk is mitigated by the total absence of executable capabilities within the skill's environment.
Audit Metadata