project-planner
Pass
Audited by Gen Agent Trust Hub on Oct 7, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and analyze untrusted external data, such as user-provided project requirements, design documents, and technical plans. It also has access to powerful tools including the Bash shell and filesystem manipulation tools (Read, Write, Edit). The absence of explicit boundary markers or instructions to the agent on how to safely handle and sanitize this external data creates an attack surface for indirect prompt injection.
- Ingestion points: User-provided text queries and uploaded reference documents mentioned in the 'Provide detailed information' section.
- Boundary markers: None present to delimit external data from instructions.
- Capability inventory: Bash, Read, Write, Edit, TodoWrite, Glob, Grep.
- Sanitization: No sanitization or validation of the ingested content is specified.
Audit Metadata