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