basecamp-automation
Pass
Audited by Gen Agent Trust Hub on Mar 13, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill requires users to connect to a remote MCP server at
https://rube.app/mcpto function. - [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection through the processing of external data.
- Ingestion points: Untrusted content is ingested from Basecamp using tools like
BASECAMP_GET_MESSAGEandBASECAMP_GET_BUCKETS_TODOLISTS_TODOS(SKILL.md). - Boundary markers: There are no defined boundary markers or instructions provided to the agent to disregard instructions within the ingested data.
- Capability inventory: The skill possesses high-privilege capabilities, most notably
BASECAMP_PUT_PROJECTS_PEOPLE_USERS, which allows for granting/revoking project access and creating new users (SKILL.md). - Sanitization: There is no evidence of content sanitization or validation for the data retrieved from Basecamp before it is utilized by the agent.
Audit Metadata