codebase-onboarding

Pass

Audited by Gen Agent Trust Hub on Apr 14, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it instructs the agent to systematically analyze and map content from potentially untrusted external codebases.
  • Ingestion points: The agent reads various codebase files including package manifests (e.g., package.json, go.mod), configuration files, and documentation during the reconnaissance phase (SKILL.md).
  • Boundary markers: No delimiters or specific instructions to 'ignore embedded instructions' are provided to prevent the agent from obeying malicious commands found within the analyzed data.
  • Capability inventory: The underlying agent typically possesses file system access (read_file, ls) and shell execution capabilities which could be leveraged if an injection is successful.
  • Sanitization: There is no mention of sanitizing or validating the contents of the files before the agent processes and incorporates them into the onboarding artifacts.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 14, 2026, 12:19 AM
Security Audit — agent-trust-hub — codebase-onboarding