basecamp-automation
Pass
Audited by Gen Agent Trust Hub on Oct 29, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from Basecamp projects and messages, creating an attack surface where embedded instructions could influence the agent's behavior.
- Ingestion points: The skill retrieves project details, to-do lists, and message board content using tools such as
BASECAMP_GET_PROJECTS,BASECAMP_GET_BUCKETS_TODOLISTS_TODOS, andBASECAMP_GET_MESSAGE(documented in SKILL.md). - Boundary markers: There are no explicit instructions or delimiters provided to the agent to distinguish between data and instructions within the ingested content.
- Capability inventory: The skill has broad write capabilities, including posting to message boards, creating tasks, and managing project access (granting/revoking permissions) via
BASECAMP_PUT_PROJECTS_PEOPLE_USERS. - Sanitization: The instructions do not define any sanitization, filtering, or validation steps for the content retrieved from external Basecamp sources before it is processed by the agent.
Audit Metadata