folder-management
Pass
Audited by Gen Agent Trust Hub on Apr 16, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it ingests and processes untrusted strings (such as folder names, descriptions, and file metadata) retrieved from the Spuree API without implementing boundary markers or sanitization to prevent these strings from influencing agent behavior.
- Ingestion points: Untrusted data is retrieved from the children, assets, and files endpoints described in SKILL.md.
- Boundary markers: The instructions do not provide delimiters or specific guidelines for the agent to ignore potentially malicious content within these strings.
- Capability inventory: The skill enables the agent to perform create, update, and delete operations on the project structure and to retrieve presigned URLs for file downloads.
- Sanitization: There is no evidence of input validation or escaping for the data returned from the remote API.
Audit Metadata