skills/obra/superpowers/writing-plans/Gen Agent Trust Hub

writing-plans

Pass

Audited by Gen Agent Trust Hub on Mar 26, 2026

Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
  • [PROMPT_INJECTION]: The skill processes untrusted project specifications to generate implementation plans, which creates a potential surface for indirect prompt injection where malicious instructions in the input could influence the generated output.
  • Ingestion points: Technical requirements and specifications documents are the primary input for the planning process.
  • Boundary markers: The skill lacks explicit delimiters or instructions to ignore embedded commands or instructions within the ingested specifications.
  • Capability inventory: The skill is designed to generate plans that include file system modifications and shell command execution (e.g., git, pytest).
  • Sanitization: No sanitization or validation logic is specified for the input data before it is incorporated into the planning process.
  • [COMMAND_EXECUTION]: The skill instructs the agent to generate and potentially execute implementation plans containing shell commands for testing (pytest) and version control (git). while standard for development, these commands are derived from the generated plan which is influenced by external input.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 26, 2026, 09:29 AM