exec-report
Pass
Audited by Gen Agent Trust Hub on Jun 20, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface through its ingestion of external data from SharePoint and CSVs.\n
- Ingestion points: Untrusted data is retrieved from SharePoint lists and CSV exports as described in SKILL.md (Step 1).\n
- Boundary markers: There are no instructions to use delimiters or ignore embedded commands when processing external data.\n
- Capability inventory: The skill generates HTML/JavaScript files and saves them to the local filesystem (SKILL.md, Step 5).\n
- Sanitization: The skill lacks comprehensive output encoding or sanitization logic to ensure that malicious data does not result in code execution (XSS) or behavioral manipulation within the generated reports.
Audit Metadata