skills/h-mmer/pentest-agents/fullscan/Gen Agent Trust Hub

fullscan

Fail

Audited by Gen Agent Trust Hub on May 10, 2026

Risk Level: HIGHCOMMAND_EXECUTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill instructs the agent to perform multiple shell operations using the uv run python3 command pattern.
  • [COMMAND_EXECUTION]: User-provided $ARGUMENTS are directly interpolated into shell commands in 'Phase 0' and 'Phase 4' (e.g., uv run python3 $CLAUDE_PROJECT_DIR/tools/brain.py brief $ARGUMENTS). This structure is highly susceptible to shell command injection if a user provides input containing metacharacters such as semicolons, pipes, or backticks.
  • [COMMAND_EXECUTION]: The workflow relies on executing Python scripts located in $CLAUDE_PROJECT_DIR/tools/ (such as brain.py, scope_check.py, and dedup_findings.py) which are not included within the skill package, creating an external dependency on the local environment.
Recommendations
  • AI detected serious security threats
Audit Metadata
Risk Level
HIGH
Analyzed
May 10, 2026, 07:58 AM
Security Audit — agent-trust-hub — fullscan