omni-usage-logs
Pass
Audited by Gen Agent Trust Hub on Oct 15, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill provides access to call logs and usage history which are sources of untrusted data.
- Ingestion points: Endpoints like /api/usage/call-logs and /api/usage/request-logs in SKILL.md ingest content that may include malicious instructions from previous sessions.
- Boundary markers: There are no markers defined to help the agent distinguish between the log data and its system instructions.
- Capability inventory: The skill allows for GET, POST, and DELETE operations on a local API, providing a surface for actions if an injection is successful.
- Sanitization: The skill lacks specified sanitization for the log data it retrieves.
Audit Metadata