founder-debrief
Pass
Audited by Gen Agent Trust Hub on Mar 17, 2026
Risk Level: SAFEPROMPT_INJECTIONNO_CODE
Full Analysis
- [PROMPT_INJECTION]: Surface for indirect prompt injection exists in the meeting note processing workflow.
- Ingestion points: User-provided conversation summaries and meeting notes defined in
SKILL.md. - Boundary markers: Absent; input is processed directly without delimiters or safety instructions to ignore embedded prompts.
- Capability inventory: The agent reads and writes to business strategy files such as
canonical/objections.mdandcanonical/talk-tracks.md. - Sanitization: No evidence of input validation or sanitization before file updates.
- [NO_CODE]: The skill consists purely of markdown instructions and templates with no executable code or scripts.
Audit Metadata