cali-product-interface-alternatives
Pass
Audited by Gen Agent Trust Hub on Jul 3, 2026
Risk Level: SAFEPROMPT_INJECTIONEXTERNAL_DOWNLOADSCOMMAND_EXECUTION
Full Analysis
- [PROMPT_INJECTION]: The skill processes project-specific data from files located at
.stelow/{YYYY-MM-DD}/{_dir}/plans/spec-product_{v}.mdto drive the interface generation process. This creates a surface for indirect prompt injection where instructions embedded in these files could influence the agent's behavior. - Ingestion points:
.stelowdirectory specification files read by the agent. - Boundary markers: None identified; content is parsed directly for values like 'appetite'.
- Capability inventory: Parallel task delegation via
subagents, visual review gating viaplannotator, and shell command execution (grep,awk). - Sanitization: No explicit sanitization or filtering of the ingested file content was detected.
- [EXTERNAL_DOWNLOADS]: The documentation includes instructions to install several third-party plugins and packages from GitHub repositories (e.g.,
github.com/cursor/plugins,github.com/PriNova/pi-agent-codebase-workflows) and NPM registries. While some sources like 'cursor' are well-known, others are specific to the tool's ecosystem. - [COMMAND_EXECUTION]: The skill utilizes bash commands such as
grepandawkto automate the extraction of parameters from project files. These commands are used to transition between workflow stages based on the content of the managed codebase.
Audit Metadata