gitnexus-lfg

Pass

Audited by Gen Agent Trust Hub on Jul 19, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it ingests and processes external data to drive its orchestration logic.
  • Ingestion points: The skill reads task descriptions (user input) and plan files stored in docs/plans/ (which could be influenced by external contributors in a repository context) to determine which sub-skills to invoke.
  • Boundary markers: There are no explicit instructions or delimiters used to separate the content of plan files from the agent's orchestration instructions.
  • Capability inventory: The skill orchestrates high-capability sub-skills (gitnexus-plan, gitnexus-work, gitnexus-review) that can perform file system modifications and git operations.
  • Sanitization: No explicit sanitization or validation of the plan file content is performed before the agent processes it to decide on the next pipeline stage.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 19, 2026, 02:41 PM
Security Audit — agent-trust-hub — gitnexus-lfg