The Agent Skills Directory

[SAFE]: No malicious patterns or security risks were identified. The skill defines a structured methodology for debugging and evidence collection without code.
[NO_CODE]: The skill does not include any executable scripts, binary files, or external package dependencies.
[INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and analyze external evidence and environment details, which is a potential surface for indirect prompt injection. However, the skill's restricted environment and lack of execution capabilities mitigate this risk. Ingestion points: 'reproducible evidence, environment details, and recent changes'. Boundary markers: None identified in the markdown instructions. Capability inventory: None. The skill contains no functions for file writing, network access, or command execution. Sanitization: No sanitization or validation of the ingested evidence is specified.

mode-investigate