accessibility

Pass

Audited by Gen Agent Trust Hub on Aug 27, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from external files or components passed through the $ARGUMENTS parameter to perform accessibility checks. This ingestion process creates a potential surface for indirect prompt injection.
  • Ingestion points: The skill reads file contents and components specified in $ARGUMENTS using Read and Grep tools.
  • Boundary markers: The instructions do not define clear delimiters or boundary markers to separate the data being analyzed from the agent's instructional context.
  • Capability inventory: The agent has access to Bash, Read, Glob, and Grep, and it executes a local Python script to perform calculations.
  • Sanitization: There is no evidence of sanitization, escaping, or filtering of the ingested file content before it is processed by the agent.
  • [COMMAND_EXECUTION]: The skill instructions direct the agent to execute a local Python script to perform specific accessibility measurements.
  • Evidence: The skill calls python3 .claude/skills/ordinary-interfaces/scripts/contrast.py "#fg" "#bg" to programmatically verify color contrast values.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 27, 2026, 11:31 PM
Security Audit — agent-trust-hub — accessibility