nexus-submit-spec

Pass

Audited by Gen Agent Trust Hub on May 30, 2026

Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
  • [PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface as it processes data from external project actions and specifications.
  • Ingestion points: Data is ingested via probe action show, probe project get, and probe project spec show from files and project metadata.
  • Boundary markers: No specific delimiters or instructions to ignore embedded content are present when reading project specifications.
  • Capability inventory: The skill can perform state-changing operations via probe project spec submit and broadcast messages via probe message send.
  • Sanitization: No sanitization or validation of the ingested specification content is performed before it is passed to other tools.
  • [COMMAND_EXECUTION]: The skill uses the system sha256sum utility to verify file integrity.
  • Evidence: The workflow includes the command sha256sum <path-to-gating-spec.md> to compute hashes of local specification files.
Audit Metadata
Risk Level
SAFE
Analyzed
May 30, 2026, 02:11 AM
Security Audit — agent-trust-hub — nexus-submit-spec