sales-hiring

Pass

Audited by Gen Agent Trust Hub on Sep 13, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill ingests user-provided data through a ten-question interview process to customize hiring artifacts such as scorecards, interview loops, and ramp plans. While this creates a potential surface for indirect injection, the skill lacks the capabilities to perform dangerous operations.
  • Ingestion points: User input provided in response to the "Interview" section described in SKILL.md.
  • Boundary markers: The skill does not define specific delimiters or "ignore" instructions for the ingested user data.
  • Capability inventory: No dangerous capabilities were detected. The skill is limited to generating text-based markdown artifacts and does not involve subprocess calls, file writing, or network operations.
  • Sanitization: No explicit sanitization or filtering of external content is performed before interpolation into the output artifacts.
  • [SAFE]: No malicious patterns, including prompt injection, credential exposure, obfuscation, or remote code execution, were detected in any of the skill files.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 13, 2026, 09:17 PM
Security Audit — agent-trust-hub — sales-hiring