skills/bossjones/boss-skills/planf3/Gen Agent Trust Hub

planf3

Pass

Audited by Gen Agent Trust Hub on Sep 24, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONDYNAMIC_EXECUTIONEXTERNAL_DOWNLOADSCOMMAND_EXECUTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted user input via the user_prompt variable to generate implementation plans. These plans include implementation tasks and validation commands ({{VALIDATION_COMMAND}}) which are intended to be executed by the agent in a subsequent Build Plan workflow. This creates a surface where a malicious prompt could result in the generation and execution of harmful commands.\n
  • Ingestion points: user_prompt argument in SKILL.md.\n
  • Boundary markers: The generated HTML plan uses template placeholders but does not include explicit instructions or markers to the agent to ignore or sanitize embedded commands during the build phase.\n
  • Capability inventory: The allowed-tools includes Bash(uv run:*) and Bash(open -a:*). The Build Plan workflow (in workflows/build-plan.md) directs the agent to execute implementation tasks and validation commands defined within the generated HTML plan.\n
  • Sanitization: No sanitization or validation of the generated commands is performed before execution in the Build Plan workflow.\n- [DYNAMIC_EXECUTION]: The skill follows a pattern of generating an implementation plan in HTML format (described in workflows/create-plan.md) and subsequently executing shell commands defined within that plan (described in workflows/build-plan.md). This constitutes the dynamic generation and execution of code from templates based on user input.\n- [EXTERNAL_DOWNLOADS]: The Python scripts scripts/generate_gpt_image.py and scripts/edit_gpt_image.py declare dependencies on openai and python-dotenv in their script headers. These packages are downloaded at runtime from the official Python Package Index (PyPI) when executed via the uv tool. These are well-known and standard libraries used for OpenAI API interaction.\n- [COMMAND_EXECUTION]: The skill invokes the Bash tool to run local scripts via uv run and to open files in a web browser via open -a. Additionally, the Build Plan workflow explicitly instructs the agent to execute shell commands specified within implementation phases and validation sections of the generated plans.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 24, 2026, 04:39 AM