creating-slide-decks

Pass

Audited by Gen Agent Trust Hub on Aug 8, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The troubleshooting guide in references/troubleshooting-common.md provides a command to execute a contrast validation script (check_contrast.py) via uv run. The script path is resolved using the $DESIGNING_SLIDE_COLORS_SKILL_DIR environment variable, which is a standard pattern for inter-skill communication within this environment to ensure visual accessibility.
  • [PROMPT_INJECTION]: The workflow described in SKILL.md involves the ingestion of external project data such as briefs, content sources, and brand assets. This represents an indirect prompt injection surface.
  • Ingestion points: SKILL.md (Workflow Step 1: 'Inspect the brief, audience... content sources').
  • Boundary markers: Absent. The instructions do not specify the use of delimiters or 'ignore' instructions for untrusted data.
  • Capability inventory: The skill has access to shell command execution (uv run, svglint) and file system write capabilities.
  • Sanitization: Absent. No specific sanitization or validation steps are prescribed for the external content before it is processed by the agent.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 8, 2026, 12:13 PM
Security Audit — agent-trust-hub — creating-slide-decks