ugc-content-grader
Pass
Audited by Gen Agent Trust Hub on Sep 21, 2026
Risk Level: SAFENO_CODEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill consists of procedural instructions and scoring rubrics for evaluating video scripts. No malicious patterns, obfuscation, or unauthorized access attempts were detected.
- [NO_CODE]: The analysis confirmed that the skill files do not contain any programming code, scripts, or command-line instructions.
- [INDIRECT_PROMPT_INJECTION]: 1. Ingestion points: The skill is designed to process user-provided UGC video scripts and ideas (SKILL.md). 2. Boundary markers: No explicit delimiters or instructions to ignore embedded commands are present in the guidelines. 3. Capability inventory: The skill specifies the ability to score content and update card objects within the agent's context (SKILL.md). No network, subprocess, or file-write capabilities were found. 4. Sanitization: No input validation or sanitization logic is described. The potential risk is minimal as the agent's actions are limited to metadata updates and text transformation.
Audit Metadata