franchise-inventory
Pass
Audited by Gen Agent Trust Hub on Sep 30, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process a wide variety of business data files from the local environment, which serves as a potential vector for indirect prompt injection if those files contain malicious instructions.\n
- Ingestion points: Scans the project for inventory management records (MarketMan, BlueCart, xtraCHEF, etc.), POS integration data, purchasing platforms, receiving logs, invoice matching records, and waste tracking logs.\n
- Boundary markers: The instructions do not define delimiters or specific warnings for the agent to distinguish between the skill's instructions and potentially malicious content embedded within the ingested data files.\n
- Capability inventory: The agent can read project files and write to the local file system (
docs/franchise-inventory-analysis.md). It also identifies and appends telemetry data to the~/.claude/projects/directory if present.\n - Sanitization: There are no explicit instructions for the agent to sanitize, escape, or validate the contents of the business data records before processing or including them in outputs.
Audit Metadata