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

factory

Pass

Audited by Gen Agent Trust Hub on Oct 14, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted external data from GitHub issues, specifications, or task descriptions, which could contain malicious instructions designed to influence the agent's behavior during the task-to-PR workflow.
  • Ingestion points: The skill accepts a <spec, task, or GitHub issue> as an argument and reads source repository instructions (SKILL.md).
  • Boundary markers: The instructions do not define specific delimiters or instructions to treat the external content as data rather than instructions.
  • Capability inventory: The skill has the authority to perform GitHub operations (merging PRs, updating issues) and delegates code-related tasks to the /task-to-pr skill.
  • Sanitization: There is no evidence of sanitization or filtering for instructions embedded within the external task descriptions.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 14, 2026, 09:40 AM