phlearn
Pass
Audited by Gen Agent Trust Hub on Jul 23, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: No malicious code, exfiltration patterns, or obfuscation were detected in the analyzed file. The skill is a pure text-based prompt with no executable components.
- [PROMPT_INJECTION]: The skill demonstrates an indirect prompt injection surface by ingesting user-provided topics to generate titles. The risk is safe because the skill has no access to sensitive data or dangerous tools. 1. Ingestion points: User expertise and topic (SKILL.md, Step 1). 2. Boundary markers: None. 3. Capability inventory: No subprocess calls, network operations, or file system access are permitted (restricted by disable-model-invocation: true in frontmatter). 4. Sanitization: None.
Audit Metadata