lgpd-legacy-retrofit

Warn

Audited by Gen Agent Trust Hub on Jun 28, 2026

Risk Level: MEDIUMDATA_EXFILTRATIONPROMPT_INJECTION
Full Analysis
  • [DATA_EXFILTRATION]: The skill accesses sensitive local files and infrastructure configurations.
  • It explicitly instructs the agent to read .env files and environment variables, which commonly contain sensitive secrets, credentials, and API tokens.
  • It analyzes database schemas (e.g., prisma/schema.prisma), migration files, and API endpoints, exposing the application's internal data architecture and PII locations.
  • [PROMPT_INJECTION]: The skill is vulnerable to indirect prompt injection due to its broad data ingestion surface.
  • Ingestion points: The skill reads the entire codebase, including source files, third-party SDK configurations, documentation, and metadata from various files (e.g., package.json, AndroidManifest).
  • Boundary markers: There are no instructions to use delimiters or to disregard potentially malicious instructions embedded within the files being audited.
  • Capability inventory: The agent has the ability to write analysis results back to the filesystem (.lgpd/discovery.md, .lgpd/gaps.md) and is instructed to chain to other skills based on the content found.
  • Sanitization: No validation or sanitization of the content extracted from the project files is performed before it is processed by the agent.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Jun 28, 2026, 02:52 PM
Security Audit — agent-trust-hub — lgpd-legacy-retrofit