sales-hire-scorecard
Pass
Audited by Gen Agent Trust Hub on Oct 9, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from external sources that could contain malicious instructions designed to manipulate the hiring outcome.
- Ingestion points: Data is pulled from placeholders
{{ATS}}(role, candidate feedback, interview notes) and{{NOTES_TOOL}}(interview recordings or notes) as described inSKILL.md(Step 1, Step 7). - Boundary markers: The instructions do not define any delimiters or system-level warnings to the agent to ignore instructions that might be contained within the interview feedback or notes.
- Capability inventory: The skill has the capability to write notes back to the
{{ATS}}and move candidates through workflow stages (Step 10). - Sanitization: There is no mention of sanitizing, escaping, or validating the text content retrieved from the ATS or notes tool before it is processed by the agent to generate scores and rankings.
Audit Metadata