user-flow-mapping
Pass
Audited by Gen Agent Trust Hub on Sep 17, 2026
Risk Level: SAFENO_CODEINDIRECT_PROMPT_INJECTION
Full Analysis
- [NO_CODE]: The skill is composed exclusively of Markdown documentation (SKILL.md). It does not contain any shell scripts, Python code, or configuration files that execute on the host system.
- [SAFE]: The skill does not request any sensitive permissions, perform network operations, or access the file system.
- [INDIRECT_PROMPT_INJECTION]: The skill instructions define a process for ingesting external user data to generate diagrams.
- Ingestion points: The 'Usage' section of SKILL.md indicates the agent should receive 'user goal, product context, and analytics data' from the user.
- Boundary markers: None specified in the instructions to separate user-provided data from system instructions.
- Capability inventory: None. The skill does not utilize any tools, subprocess calls, or network operations.
- Sanitization: None described for the input data.
Audit Metadata