The Agent Skills Directory

[PROMPT_INJECTION]: The skill possesses a surface for indirect prompt injection by processing external data from application logs and command output.
Ingestion points: Error logs and standard error streams are piped into the scripts/error-parser.py script for analysis via the instructions in SKILL.md.
Boundary markers: Absent. The skill does not define specific delimiters or instructions for the agent to ignore potential commands embedded within the logs.
Capability inventory: The skill uses Bash, Read, and Grep tools and provides instructions for executing interactive code via python3, node, and various database clients.
Sanitization: While the error-parser.py script extracts structured data using regular expressions, it does not explicitly sanitize the content for malicious prompt injection patterns.
[COMMAND_EXECUTION]: The skill facilitates the execution of multiple diagnostic and debugging commands.
Includes instructions and examples for executing interactive code snippets and database queries to test application state.
Executes a local helper script (scripts/error-parser.py) to process diagnostic data.
Uses the dynamic context injection syntax (!) in SKILL.md to automatically fetch recent log data using docker compose or tail when the skill is loaded, which is used for diagnostic context.

debug