diagnostics-report-analyzer-skill
Pass
Audited by Gen Agent Trust Hub on Jul 8, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill is designed to parse and interpret untrusted external data (HTML and JSON diagnostic reports), which is a common vector for indirect prompt injection. Specifically, the instructions prioritize reading the
agentHintsfield from the report's JSON payload, which is explicitly intended to guide the agent's behavior. - Ingestion points: Diagnostic reports provided via file attachments or raw text in SKILL.md parsing logic.
- Boundary markers: None. The skill does not implement delimiters or provide 'ignore embedded instructions' warnings for the data it processes.
- Capability inventory: No capabilities detected. The skill does not request or use tools for network access, file system manipulation, or shell command execution.
- Sanitization: None. The skill parses raw JSON and HTML content without sanitizing or escaping the data before interpolation into the agent context.
Audit Metadata