slack-to-teams
Pass
Audited by Gen Agent Trust Hub on Oct 22, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- Indirect Prompt Injection Surface: The skill includes procedures to scan and analyze existing project files, such as dependency manifests (
package.json,requirements.txt) and source code. This ingestion of external data represents a potential surface for indirect prompt injection, where content within the analyzed project could attempt to influence the agent's instructions. This behavior is necessary for the skill's primary purpose of automated project analysis and migration guidance. - Internal Resource Routing: The skill dynamically loads instructions from a large collection of local 'micro-expert' markdown files based on detected project characteristics. This modular approach is a standard architecture for complex AI agent tasks and does not involve risky dynamic code execution or remote resource fetching.
Audit Metadata