The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process untrusted data from user-provided files, which serves as a potential surface for indirect prompt injection.
Ingestion points: The instructions.md file specifies that the agent should accept data in common formats such as CSV, Excel, and JSON for processing.
Boundary markers: No explicit delimiters or boundary markers are defined in the instructions to separate untrusted content from the agent's instructions.
Capability inventory: The skill requests filesystem permissions in claw.json and utilizes the pandas library for data analysis as seen in SKILL.md.
Sanitization: There are no specific instructions provided for sanitizing or validating the content of the ingested files to filter out potential prompt injections.
[EXTERNAL_DOWNLOADS]: The skill references external documentation from the official OSHA standards website and the author's own domain (datadrivenconstruction.io) for compliance resources.
[COMMAND_EXECUTION]: The skill metadata indicates a requirement for the python3 binary to execute the safety checking and reporting logic described in the documentation.

safety-compliance-checker