ccc-testing

Warn

Audited by Gen Agent Trust Hub on Apr 1, 2026

Risk Level: MEDIUMCOMMAND_EXECUTIONEXTERNAL_DOWNLOADSDATA_EXFILTRATION
Full Analysis
  • [COMMAND_EXECUTION]: The script webapp-testing/scripts/with_server.py executes server commands using subprocess.Popen with shell=True. This pattern is risky if user-supplied input is passed to the server arguments without strict sanitization.
  • [EXTERNAL_DOWNLOADS]: The plankton-code-quality skill downloads external code from a community GitHub repository (alexfazio/plankton) using git clone. While Plankton is a known community tool, it is not an officially trusted vendor repository.
  • [EXTERNAL_DOWNLOADS]: The qa and qa-only skills include instructions to download and execute the Bun installer from bun.sh using the curl | bash pattern. This is a well-known service, but the execution method bypasses standard package manager safety checks.
  • [DATA_EXFILTRATION]: The Preamble sections in qa/SKILL.md and qa-only/SKILL.md contain shell commands that automatically collect and log telemetry. This includes the name of the current repository (basename "$(git rev-parse --show-toplevel)"), session IDs, and skill usage data, which are stored in ~/.gstack/analytics/ and sent to an external telemetry service.
  • [DATA_EXFILTRATION]: The skill implements session tracking by creating files in the user's home directory (~/.gstack/sessions/) named after the parent process ID ($PPID).
  • [PROMPT_INJECTION]: The qa and qa-only skills utilize a 'Completeness Principle' that strongly instructs the agent to always prefer complete implementations over shortcuts, even when not explicitly requested by the user, which could lead to unexpected resource consumption or code changes.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Apr 1, 2026, 05:35 AM
Security Audit — agent-trust-hub — ccc-testing