The Agent Skills Directory

[COMMAND_EXECUTION]: The skill uses the kensa command-line interface to generate reports and analyze traces (e.g., kensa report --format json, kensa analyze --format json). This is the intended functionality of the skill within its ecosystem.
[PROMPT_INJECTION]: The skill exhibits a surface for indirect prompt injection because it ingests and processes untrusted data from evaluation results.
Ingestion points: Processes data from the latest results file in .kensa/results/ and trace logs in .kensa/traces/, which may contain strings generated by other agents or external systems.
Boundary markers: Absent. The instructions do not specify the use of delimiters or warnings to ignore potentially malicious instructions embedded within the reasoning or evidence fields of judge results.
Capability inventory: The skill has the ability to execute shell commands using the kensa CLI.
Sanitization: Absent. There is no mention of validating or escaping content read from JSONL trace files or evaluation results before the agent processes them.

diagnose-errors