business-plan
Pass
Audited by Gen Agent Trust Hub on Nov 8, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill exhibits an attack surface for indirect prompt injection by reading and processing existing files from the local filesystem during 'UPDATE' and 'FIND' operations.
- Ingestion points: The skill reads existing plans from directories such as
business/,strategy/,plans/, anddocs/business/as specified in the 'Search Locations' section ofSKILL.md. - Boundary markers: The instructions do not specify any delimiters or safety markers to differentiate between the agent's instructions and the content retrieved from the files.
- Capability inventory: The skill allows the agent to write updated content back to markdown files on the filesystem.
- Sanitization: There is no evidence of sanitization or filtering applied to the content of existing files before they are loaded into the agent's context.
Audit Metadata