pixta-metadata

Pass

Audited by Gen Agent Trust Hub on Feb 17, 2026

Risk Level: SAFENO_CODE
Full Analysis
  • [No Code] (SAFE): The skill consists entirely of four Markdown files (SKILL.md, EXAMPLES.md, TAG_CATEGORIES.md, TITLE_GUIDE.md). No Python packages, Node.js packages, shell scripts, or other executable files are present.
  • [Prompt Injection] (SAFE): The skill is designed to process user-provided image prompts (Category 8 surface). 1. Ingestion points: The image prompts are accepted as inputs in the PIXTA workflow described in SKILL.md. 2. Boundary markers: None are defined in the instructions. 3. Capability inventory: The skill possesses no tools, network access, file system access, or command execution capabilities. 4. Sanitization: No input validation is performed. Conclusion: While the skill processes untrusted data, the total absence of operational capabilities ensures that any potential indirect prompt injection is non-exploitable beyond basic text manipulation.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 17, 2026, 06:37 PM