subscription-auditor
Pass
Audited by Gen Agent Trust Hub on Sep 20, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process data from external sources that are not fully controlled by the user, such as transaction descriptions in credit card statements and the bodies of receipt emails. These sources could be used to deliver malicious instructions to the agent.\n- Ingestion points: The skill reads statement exports in CSV or PDF format and scans receipts-email folders (SKILL.md).\n- Boundary markers: The skill does not define specific delimiters or instructional barriers to prevent the agent from following commands embedded within the transaction or email data.\n- Capability inventory: The agent has the capability to read local files, read emails, navigate to web portals, take screenshots, and draft emails (SKILL.md).\n- Sanitization: There are no provisions for sanitizing or validating the input data to filter out potential injection strings before processing.
Audit Metadata