founder-brand
Pass
Audited by Gen Agent Trust Hub on Oct 7, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingests data from several local files to generate branding candidates and briefs. This creates a potential surface for indirect prompt injection if the source files contain malicious instructions.\n
- Ingestion points: Reads from founder/idea.md, founder/marketing.md, founder/competitors.md, and founder/panel/results.md in Step 1.\n
- Boundary markers: The skill does not define specific delimiters or instructions to ignore commands within the ingested content.\n
- Capability inventory: The agent is instructed to write the results to founder/brand.md and may invoke an image generation tool if available.\n
- Sanitization: No sanitization or filtering of the ingested file content is specified.
Audit Metadata