onboard

Pass

Audited by Gen Agent Trust Hub on May 14, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill is subject to indirect prompt injection (Category 8) because its primary function involves ingesting and interpreting the contents of an untrusted codebase.
  • Ingestion points: The agent reads the local project structure, source code files, and build configurations as part of the analysis procedure (SKILL.md).
  • Boundary markers: No explicit delimiters or boundary markers are defined to separate the instructions from the data extracted from the codebase.
  • Capability inventory: The skill possesses file system read access to analyze the codebase and write access to create 'CODEBASE.md' and 'PRESENTATION.md'. It is configured to run in a 'fork' context, which limits the scope of its execution environment.
  • Sanitization: The instructions do not describe any sanitization, filtering, or validation of the content read from the source files before it is processed by the model.
Audit Metadata
Risk Level
SAFE
Analyzed
May 14, 2026, 09:58 AM
Security Audit — agent-trust-hub — onboard