skills/owainlewis/blueprint/spec/Gen Agent Trust Hub

spec

Pass

Audited by Gen Agent Trust Hub on Nov 11, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted input from user requests and existing project documentation which could contain malicious instructions.
  • Ingestion points: The process in SKILL.md requires reading user requests, project code, REQUIREMENTS.md, and ARCHITECTURE.md.
  • Boundary markers: There are no defined delimiters or instructions to the agent to ignore potentially malicious embedded commands within these external files.
  • Capability inventory: The skill is capable of filesystem writes (creating spec files in docs/ or updating tickets) and executing shell commands for configuration.
  • Sanitization: No sanitization, escaping, or validation logic is specified for the content retrieved from external files before processing.
  • [COMMAND_EXECUTION]: The skill performs shell command execution to gather metadata.
  • Evidence: SKILL.md instructs the agent to "Take the author from the request, or else from git config user.name."
Audit Metadata
Risk Level
SAFE
Analyzed
Nov 11, 2026, 08:17 AM