uipath-project-knowledge-base
Pass
Audited by Gen Agent Trust Hub on Jul 31, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: No malicious patterns, prompt injections, or obfuscation techniques were detected in the skill instructions or metadata.
- [DATA_EXFILTRATION]: No network access or sensitive file reading commands were identified. The skill includes a guardrail stating 'Do not put credentials, personal data, or unrestricted production records in the knowledge base.'
- [REMOTE_CODE_EXECUTION]: The skill does not contain any code, package dependencies, or instructions for downloading and executing remote scripts.
- [PROMPT_INJECTION]: The skill performs ingestion of external project data which presents a theoretical surface for indirect prompt injection, but the lack of executable capabilities makes this a low-risk finding.
- Ingestion points:
SKILL.mdreferences inventorying existing Markdown, SDDs, ADRs, and research notes. - Boundary markers: Absent.
- Capability inventory: The skill only produces Markdown text and does not use any tools or shell commands.
- Sanitization: Absent.
Audit Metadata