post-demo
Pass
Audited by Gen Agent Trust Hub on Mar 7, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [SAFE]: No malicious patterns detected in the skill code or logic. All file access is restricted to local context files (company profile and prep documents) necessary for the primary sales use-case.\n- [PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface through the processing of user-supplied meeting notes and transcripts.\n
- Ingestion points: Meeting notes and transcripts in
SKILL.md.\n - Boundary markers: Absent; transcripts are processed as raw text.\n
- Capability inventory: None; the skill is limited to text generation and lacks network, file-write, or command execution capabilities.\n
- Sanitization: None detected.
Audit Metadata