The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill ingests and analyzes trace logs generated from an external debuggee process. These logs include labels and comments which are attacker-controllable if the debugged binary is malicious. Instructions hidden in these fields could attempt to influence the agent's behavior during the analysis phase.
Ingestion points: The skill reads the trace log file (./traces/trace_<timestamp>.log) in Step 5.
Boundary markers: There are no specific delimiters or instructions to the agent to disregard potential commands found within the labels or comments of the trace log.
Capability inventory: The skill uses Bash, Read, and various mcp__x64dbg tools, which could be targeted by a successful injection.
Sanitization: No sanitization or filtering of the log content is performed before the agent processes and summarizes the data.
[COMMAND_EXECUTION]: The skill uses the Bash tool to create the ./traces/ directory if it does not exist. This is a functional requirement for the skill to store its output and is used legitimately within the described workflow.

tracealyzer