sales-hiring-brief
Pass
Audited by Gen Agent Trust Hub on Nov 1, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process external candidate documents (CVs) to generate rankings and scorecards, creating a potential surface for indirect prompt injection attacks where a resume could contain hidden directives.
- Ingestion points: External candidate CVs provided by the user (SKILL.md, "Process" step 8).
- Boundary markers: The skill does not define specific delimiters or instructions for the agent to ignore potentially embedded malicious prompts within the CV text.
- Capability inventory: The skill is capable of generating markdown output, creating Notion pages (if a connector is present), and generating .docx files through secondary skills.
- Sanitization: No specific sanitization or filtering logic is provided to handle untrusted text from the ingested CVs.
Audit Metadata