project
Pass
Audited by Gen Agent Trust Hub on Oct 14, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill exposes a surface for indirect prompt injection by ingesting and acting upon content from external vault files.\n
- Ingestion points: The skill reads
../vault/SKILL.md,AGENTS.md, active Project templates, and existing Project notes to inform its operations.\n - Boundary markers: There are no boundary markers or instructions instructing the agent to disregard instructions that might be embedded in the files it reads.\n
- Capability inventory: The skill utilizes a
vaultsafe-write tool to create and update files and has the ability to move files to archive locations.\n - Sanitization: There is no evidence of sanitization or content validation for data retrieved from the vault before it is used to generate or modify notes.
Audit Metadata