The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and analyze untrusted external data, specifically stack traces, logs, and error messages, which creates a potential surface for indirect prompt injection attacks.\n- Ingestion points: The skill explicitly processes error messages, exceptions, and log analysis data as part of its core debugging function (SKILL.md).\n- Boundary markers: There are no instructions for the agent to use delimiters or ignore instructions embedded within the logs or traces being analyzed.\n- Capability inventory: The core workflow involves file manipulation and command execution for reproduction and testing (SKILL.md), which could be targeted by a successful injection.\n- Sanitization: The skill does not provide instructions for sanitizing or escaping the content of the logs or stack traces before processing.

debugging-wizard