finance-billing-ops
Pass
Audited by Gen Agent Trust Hub on Jul 29, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill possesses an indirect prompt injection surface due to its requirement to ingest and analyze untrusted external data sources.
- Ingestion points: The skill ingests live billing data, Stripe sales records, customer activity logs, and source code from sibling GitHub repositories (SKILL.md).
- Boundary markers: Absent; no specific delimiters or instructions are provided to the agent to distinguish between its primary instructions and potentially malicious commands embedded within the processed data.
- Capability inventory: The skill is authorized to read source code (via github-ops) and access financial data APIs, creating a path for ingested instructions to influence agent behavior.
- Sanitization: Absent; no explicit validation or filtering of external content is defined for the agent before processing.
Audit Metadata