The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and analyze external, potentially untrusted data such as Java stack traces, application logs, and thread dumps. This creates a surface for indirect prompt injection attacks where an attacker could embed instructions within log files to manipulate the agent's behavior.
Ingestion points: The skill accepts "any Java error, exception, or log" as input for analysis as described in the "Quick Start" and "Step 2" sections of SKILL.md.
Boundary markers: There are no instructions provided to the agent to use specific delimiters or to disregard natural language instructions found within the logs/traces being processed.
Capability inventory: The skill utilizes tools with significant system access, including Bash, Read, Grep, and Glob.
Sanitization: The skill lacks explicit instructions for the agent to sanitize or validate the content of the logs before processing them.
[COMMAND_EXECUTION]: The skill provides instructions and examples for executing shell commands using the Bash tool to perform diagnostics and build operations (e.g., mvn dependency:tree, gradle dependencies, kill -3, and jar tf). While these are standard developer operations, the combination of shell access with the ingestion of untrusted log data increases the potential impact of a prompt injection attack.

java-best-practices-debug-analyzer