remofirst-core-workflow-b

Pass

Audited by Gen Agent Trust Hub on Sep 12, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill ingests data from external API endpoints (e.g., payroll summaries, payslips, and benefits data) which could potentially contain malicious instructions if the source is compromised.\n
  • Ingestion points: API responses from /payroll, /employees/{id}/payslips, and /employees/{id}/benefits mentioned in SKILL.md.\n
  • Boundary markers: The provided instructions lack explicit delimiters or "ignore embedded instructions" warnings for the data being printed.\n
  • Capability inventory: The skill has access to Write, Edit, and Bash tools as defined in the frontmatter.\n
  • Sanitization: No sanitization or validation of the API response content is shown in the example code blocks.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 12, 2026, 07:17 PM
Security Audit — agent-trust-hub — remofirst-core-workflow-b