accessibility

Pass

Audited by Gen Agent Trust Hub on Oct 23, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and analyze external source code from the src/ directory, creating a vulnerability to indirect prompt injection where malicious instructions hidden in the code could influence the agent.
  • Ingestion points: Content from files matching src/**/*.* is read into the agent's context during the audit process.
  • Boundary markers: Absent. There are no instructions provided to the agent to use delimiters or to disregard instructions found within the code being analyzed.
  • Capability inventory: The skill uses Read, Write, and Edit tools, meaning an injection could potentially lead to unauthorized code modifications.
  • Sanitization: The skill does not perform any sanitization or validation of the ingested code content before the AI processes it.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 23, 2026, 07:29 PM