sync-plugin-skills

Pass

Audited by Gen Agent Trust Hub on Mar 1, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill design includes an indirect prompt injection surface.
  • Ingestion points: The skill reads implementation files from the synapse/ directory and markdown documentation from README.md and the guides/ folder.
  • Boundary markers: There are no markers or specific instructions to prevent the agent from following commands that might be embedded in the files being read.
  • Capability inventory: The skill is authorized to update and write to multiple markdown files within the plugins/synapse-a2a/skills/ directory.
  • Sanitization: No sanitization or validation logic is provided to handle potentially malicious content from the source files before it is incorporated into the skill documentation.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 1, 2026, 06:32 AM