Skills
Navigate
skills/tdimino/claude-code-minoan/photo-to-slack-emoji/Gen Agent Trust Hub

photo-to-slack-emoji

Pass

Audited by Gen Agent Trust Hub on Nov 1, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill interpolates user-provided text descriptions directly into system prompts for the Google Gemini API without sanitization or boundary markers.
  • Ingestion points: User input enters via the description and custom_prompt parameters in core/photo_to_emoji.py and the edit_prompt in edit_image.py.
  • Boundary markers: There are no delimiters or instructions used to separate untrusted user input from system instructions in the generated prompts.
  • Capability inventory: The skill has access to the local filesystem for reading/writing images and the network for communicating with the Gemini API.
  • Sanitization: The skill does not perform any validation or filtering on user-provided strings before using them in API calls.
Audit Metadata
Risk Level
SAFE
Analyzed
Nov 1, 2026, 10:13 AM