validate-marketplace
Pass
Audited by Gen Agent Trust Hub on Mar 28, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill uses the Bash tool to execute a local maintenance script
scripts/validate_marketplace.pyusing Python 3. - [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection as it is designed to ingest and validate third-party marketplace components, including other skills and plugin configurations. Maliciously crafted content within those components could attempt to influence the agent's final report or subsequent actions.
- Ingestion points: Marketplace files, skill definitions, and plugin manifests processed by the validation script.
- Boundary markers: No specific delimiters or safety instructions are provided to the agent to distinguish between validation data and instructions.
- Capability inventory: Provides execution of shell commands through the Bash tool.
- Sanitization: No explicit sanitization or filtering of the processed content is documented in the instructions.
Audit Metadata