rc-api
Pass
Audited by Gen Agent Trust Hub on Aug 8, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill instructions guide the agent to perform catalog management tasks by executing local Python scripts such as
bootstrap_catalog.pyandlist_catalog.py. This is an expected part of the skill's automation workflow. - [PROMPT_INJECTION]: The skill is subject to an indirect prompt injection attack surface as it ingests and acts upon data from the RevenueCat API.
- Ingestion points: Catalog metadata (products, entitlements, offerings) retrieved from the RevenueCat API via MCP tools (e.g.,
list-products) or the REST API endpoints defined incatalog-patterns.md. - Boundary markers: Absent. The skill does not define specific delimiters or instructions to treat external API data as untrusted content.
- Capability inventory: The agent has significant capabilities, including catalog mutation via MCP tools (
create-product,attach-products-to-package) and the execution of shell commands. - Sanitization: Absent. There are no instructions for validating or sanitizing the content of API responses before the agent processes them.
Audit Metadata