yds-data-validation

Pass

Audited by Gen Agent Trust Hub on Aug 20, 2026

Risk Level: SAFECREDENTIALS_UNSAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [DATA_EXPOSURE_AND_EXFILTRATION]: The skill resolves data sources by reading sensitive files like .env.test or .env.local to retrieve connection strings.
  • [COMMAND_EXECUTION]: The skill allows the agent to run project-defined read-only data scripts, which represents a vector for executing local code.
  • [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted project data (fixtures, seeds, and database records) which could contain malicious instructions.
  • Ingestion points: Phase 1.1 and Phase 2.
  • Boundary markers: The skill does not define specific delimiters for separating data from instructions.
  • Capability inventory: The agent can execute local shell scripts and perform database reads.
  • Sanitization: PII masking is implemented for samples in Phase 2.6.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 20, 2026, 12:49 PM
Security Audit — agent-trust-hub — yds-data-validation