flores-founder-content-machine
Pass
Audited by Gen Agent Trust Hub on Oct 8, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill possesses an attack surface for indirect prompt injection as it is designed to process untrusted data from external sources.
- Ingestion points: The procedure in
SKILL.md(Step 5) and the rules inreferences/method.md(Section 4) instruct the agent to ingest and work from external interview transcripts and founder notes. - Boundary markers: The provided instructions do not include specific boundary markers or delimiters to isolate untrusted input from the agent's core instructions.
- Capability inventory: The skill does not possess dangerous capabilities; no tool calls for file writing, network access, or command execution are requested or present in the scripts.
- Sanitization: No explicit sanitization or filtering of external text is defined in the workflow.
Audit Metadata