cc-monitor-tool
Pass
Audited by Gen Agent Trust Hub on Aug 13, 2026
Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [PROMPT_INJECTION]: The skill is designed to ingest and act upon untrusted external data streams, creating an attack surface for instructions embedded in logs or CI outputs. 1. Ingestion points: Data is ingested from 'server.log', CI outputs, and process streams as described in SKILL.md. 2. Boundary markers: The instructions lack explicit delimiters or 'ignore embedded instructions' warnings for the data being monitored. 3. Capability inventory: The skill uses Bash and Write tools to perform autonomous actions like patching code, pushing to repositories, and restarting servers based on external events. 4. Sanitization: No sanitization or content filtering is described for the incoming event streams before the agent processes them.
- [COMMAND_EXECUTION]: The skill facilitates the execution of background shell commands via the Bash tool to monitor logs and manage development environments, which is the primary intended function of the monitor tool but involves high-privilege operations.
Audit Metadata