The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill provides instructions for the agent to ingest and analyze external documentation such as original blueprints, building permits, survey maps, and historical records. This creates a potential attack surface for indirect prompt injection if an attacker were to include malicious instructions within these processed files.
Ingestion points: House blueprints, property records, historical archives, and insurance inspection records (SKILL.md).
Boundary markers: The instructions do not define specific delimiters or warnings to separate the content of external documents from the agent's core instructions.
Capability inventory: The skill utilizes powerful tools including Bash, WebFetch, Write, and Edit.
Sanitization: There are no mechanisms described for sanitizing or validating the text content extracted from these external documents before processing.

panic-room-finder