app-planner
Pass
Audited by Gen Agent Trust Hub on Mar 17, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it processes untrusted user data to generate planning documents.
- Ingestion points: The skill triggers on and processes user-provided descriptions of app ideas, workflow notes, and user interview results.
- Boundary markers: None present. The skill does not define specific delimiters or instructions to help the agent distinguish between user data and its own design-planning logic.
- Capability inventory: The skill has the capability to write markdown files to the local filesystem (e.g.,
docs/design-plans/), creating a potential vector for malicious content to be saved into the project environment. - Sanitization: Absent. No input validation, filtering, or sanitization steps are defined to secure user-supplied content before it is incorporated into the generated plan.
Audit Metadata