The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill processes data from external sources via realestate-us and realestate-in. This introduces a vulnerability surface where malicious instructions could be embedded in the retrieved rental listings or census data to influence the agent's behavior.
Ingestion points: External data retrieved through realestate-us and realestate-in commands in SKILL.md.
Boundary markers: None identified; instructions do not specify delimiters or warnings for the agent to ignore instructions within the retrieved data.
Capability inventory: The skill uses the bash tool for command execution and has file-write access to the /tmp directory as specified in SKILL.md.
Sanitization: No sanitization or validation of the external content is mentioned before processing.
[COMMAND_EXECUTION]: The skill relies on the execution of shell commands including realestate-us, realestate-in, and jq via the bash tool to perform its primary functions. While the environment is described as a read-only shell, it explicitly permits writing to the /tmp directory.

rental-market