tauri-desktop-debugging
Pass
Audited by Gen Agent Trust Hub on Sep 4, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest external data for debugging purposes.
- Ingestion points: The agent is instructed to collect evidence from WebView console logs, Rust logs, and IPC messages as described in SKILL.md and references/01-evidence-and-triage.md.
- Boundary markers: There are no explicit instructions for using delimiters when the agent processes this external data.
- Capability inventory: The skill references external workflow tools but does not define internal execution capabilities in its frontmatter.
- Sanitization: The skill includes a 'Safe Debugging' section in references/01-evidence-and-triage.md that explicitly requires redacting secrets, personal data, and tokens before use, which serves as a mitigation for data exposure.
Audit Metadata