hmw-opportunities

Pass

Audited by Gen Agent Trust Hub on Feb 28, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill utilizes an indirect prompt injection surface by reading content from the 'context/' folder and specific exercise files to build background understanding for the AI.
  • Ingestion points: Reads all files within the 'context/' directory and specifically targets 'problem-framing.md', 'sprint-roles.md', and 'hmw-opportunities.md' for session context.
  • Boundary markers: No specific boundary markers or 'ignore' instructions are used to separate the ingested file data from the core facilitation logic.
  • Capability inventory: The skill is limited to reading and writing local markdown and configuration files within the working directory. It does not have network access or command execution capabilities.
  • Sanitization: There is no evidence of sanitization or validation of the data read from files before it is provided to the agent.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 28, 2026, 03:25 AM