The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and analyze untrusted runtime data from external web applications, creating a surface for indirect prompt injection.
Ingestion points: The reticle_observe tool (for console and network logs) and reticle_look tool (for application state) ingest external data into the agent's context as described in SKILL.md.
Boundary markers: The instructions do not specify the use of delimiters or instructions to ignore potential commands embedded within the application data.
Capability inventory: The skill has the capability to perform actions via reticle_act_and_wait and execute internal tools via reticle_run based on the data it analyzes in SKILL.md.
Sanitization: There is no evidence of sanitization, filtering, or escaping of the ingested application content before it is processed by the agent.
[EXTERNAL_DOWNLOADS]: The skill provides instructions to fetch troubleshooting documentation and technical specifications from the vendor's official domain (docs.reticle.sh).

debug-broken-ui