audit-my-app
Pass
Audited by Gen Agent Trust Hub on Oct 30, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes live data from web applications, such as console errors, API responses, and element identifiers, which could contain instructions designed to influence the agent.\n
- Ingestion points: Results from
reticle_run(anomalies, visited elements, network logs, and reconciliation results) inSKILL.md.\n - Boundary markers: None specified.\n
- Capability inventory: Tool calls for application interaction (
reticle_run) and element inspection (reticle_look).\n - Sanitization: Not specified.\n- [EXTERNAL_DOWNLOADS]: The skill fetches documentation from the official vendor site to orient the agent on tool capabilities.\n
- Evidence:
curl https://docs.reticle.sh/capabilities.mdandcurl https://docs.reticle.sh/llms.txtinSKILL.md.
Audit Metadata