The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill is designed to analyze external, untrusted data including error messages, log entries, and stack traces as part of its core debugging workflow.
Ingestion points: The agent is triggered to parse and correlate log entries and error messages as defined in the skill triggers and description in SKILL.md.
Boundary markers: There are no defined boundary markers or specific instructions for the agent to ignore or isolate instructions that might be embedded within logs or error tracebacks.
Capability inventory: The skill provides templates and commands for interacting with the environment via tools like git, python, node, and dlv, which could be misused if the agent executes instructions found in the data it is analyzing.
Sanitization: The instructions do not include steps to sanitize, filter, or validate the content of the ingested logs or stack traces before processing.

debugging-wizard