skills/venhdev/skills/writing-plans/Gen Agent Trust Hub

writing-plans

Pass

Audited by Gen Agent Trust Hub on Jun 23, 2026

Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
  • [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it ingests untrusted data (specifications/requirements) to generate structured implementation tasks.\n
  • Ingestion points: Project specifications and requirements provided by the user (referenced in SKILL.md).\n
  • Boundary markers: No explicit delimiters or instructions are provided to the agent to treat the input specification as potentially untrusted content.\n
  • Capability inventory: The generated plans include Python code blocks and shell commands (pytest, git) intended for execution by other skills like superpowers:executing-plans.\n
  • Sanitization: The skill does not define methods for sanitizing or validating the contents of the input spec before incorporating it into the plan.\n- [COMMAND_EXECUTION]: The skill templates include direct instructions to generate and later execute shell commands such as pytest and git commit. While these are legitimate developer actions, the commands are dynamically constructed based on the content of the provided specification.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 23, 2026, 08:03 AM
Security Audit — agent-trust-hub — writing-plans