factory-mcp
Pass
Audited by Gen Agent Trust Hub on Oct 30, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to process data from untrusted external sources, such as Slack threads and Linear tickets, which could contain malicious instructions.
- Ingestion points: External data is ingested from Slack, Linear, and various task descriptions.
- Boundary markers: There are no explicit instructions or delimiters to isolate untrusted data from the agent's core instructions.
- Capability inventory: The skill involves bundling local files for cloud transmission and pulling cloud tasks for local testing, indicating file system access and network capabilities via the associated MCP tools.
- Sanitization: No sanitization or validation logic for the external content is mentioned in the skill definition.
Audit Metadata