troubleshoot
Pass
Audited by Gen Agent Trust Hub on Sep 19, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill incorporates external data via the
$ARGUMENTSplaceholder at the end of the file without using boundary markers. - Ingestion points:
SKILL.mduses$ARGUMENTSto receive input for troubleshooting analysis. - Boundary markers: None identified. The input is appended directly to the instruction set without delimiters.
- Capability inventory: The skill does not define its own capabilities but is intended for use by agents with existing file system and command execution tools.
- Sanitization: There is no evidence of input validation or escaping for the processed arguments.
Audit Metadata