create-profile-atlas

Pass

Audited by Gen Agent Trust Hub on Sep 11, 2026

Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill executes a bundled Python script, scripts/profile_atlas_postprocess.py, to perform image processing tasks. This script is called via the shell with arguments including paths to generated images and lists of emoji names.
  • [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted user data, including reference images and emoji shortcode names. These inputs are used as prompts for image generation and as command-line arguments for the post-processing script.
  • Ingestion points: Subject reference images and shortcode prefixes provided by the user in SKILL.md.
  • Boundary markers: No specific delimiters or warnings are used when processing user-provided shortcode names.
  • Capability inventory: The skill executes a local Python script and interacts with the agent-slack tool for searching, getting, and adding emojis.
  • Sanitization: No explicit sanitization of shortcode names is performed before they are passed as arguments to the Python script.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 11, 2026, 04:08 AM
Security Audit — agent-trust-hub — create-profile-atlas