marketplace-sync
Pass
Audited by Gen Agent Trust Hub on Oct 9, 2026
Risk Level: SAFE
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes content from plugin documentation to generate marketing metadata, creating a potential surface for indirect instructions.
- Ingestion points:
scripts/sync-marketplace.pyreads markdown and JSON files from the plugins directory. - Boundary markers: No explicit delimiters are used in the prompt instructions to isolate external content.
- Capability inventory: The skill allows the agent to read plugin files and write to docs/plugins.json.
- Sanitization: Text from documentation files is processed without validation or filtering for prompt injection patterns.
Audit Metadata