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

status

Pass

Audited by Gen Agent Trust Hub on May 10, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill instructs the agent to run a shell command: uv run python3 $CLAUDE_PROJECT_DIR/tools/statusline.py. This is intended to display an engagement dashboard and uses a local script within the project tools directory.\n- [PROMPT_INJECTION]: A potential surface for indirect prompt injection exists because the agent is instructed to process data from external sources (findings, scope, program info) and use it to drive decision-making.\n
  • Ingestion points: Output from the $CLAUDE_PROJECT_DIR/tools/statusline.py script as processed in SKILL.md.\n
  • Boundary markers: Absent; there are no delimiters or instructions to treat the dashboard data as untrusted or to ignore embedded commands.\n
  • Capability inventory: The agent is authorized to execute follow-up commands (e.g., /sync, /brain, /fullscan) based on the dashboard state.\n
  • Sanitization: Absent; the skill does not specify any validation or sanitization for the data returned by the status script.
Audit Metadata
Risk Level
SAFE
Analyzed
May 10, 2026, 07:58 AM
Security Audit — agent-trust-hub — status