conformetry-validate

Pass

Audited by Gen Agent Trust Hub on Oct 22, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from local files which could contain malicious instructions designed to influence the agent's behavior.
  • Ingestion points: The agent reads and analyzes existing code "instances" across various file types including TypeScript, Python, JSON, Markdown, and Jupyter Notebooks located in the user's workspace (e.g., packages/widgets/src/modules/orders/orders.service.ts).
  • Boundary markers: There are no explicit delimiters or instructions provided to the agent to treat the content of the analyzed files as untrusted or to ignore any embedded instructions that might be present in comments or documentation.
  • Capability inventory: The agent is instructed to modify the local filesystem to "add what is missing" or "edit the instance by hand" based on the validation reports, which allows for potentially malicious instructions in the analyzed files to be carried out during the remediation step.
  • Sanitization: The skill does not describe any sanitization, filtering, or validation of the file content before it is processed by the agent.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 22, 2026, 01:56 PM