context-level
Pass
Audited by Gen Agent Trust Hub on Oct 3, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: No security issues were identified. The skill implements a monitoring tool
mcp__context-level__readwhich provides internal session telemetry without external dependencies. - [DATA_EXFILTRATION]: The skill does not access sensitive files or environment variables and does not perform any network operations. Data access is restricted to the current session's usage metrics provided by the platform.
- [COMMAND_EXECUTION]: The skill does not execute any shell commands, scripts, or external binaries. The implementation is limited to calculating a percentage from a local API call.
- [PROMPT_INJECTION]: The instructions in SKILL.md are purely functional and do not attempt to override system prompts, bypass safety guidelines, or extract internal instructions.
- [OBFUSCATION]: The code is provided in plain text and does not use encoding, hidden characters, or any techniques to mask behavior or URLs.
Audit Metadata