axiom-analyze-crash
Pass
Audited by Gen Agent Trust Hub on Apr 26, 2026
Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
- [COMMAND_EXECUTION]: The skill directs the agent to execute the
xcsymtool and standard shell commands likecommand -vto perform its diagnostic functions. This is consistent with its role as a technical analysis tool. - [PROMPT_INJECTION]: The skill exposes a surface for Indirect Prompt Injection by processing user-supplied crash logs (
.ipsfiles). While these logs are technical in nature, the data is untrusted. - Ingestion points: User-provided crash log files in
SKILL.md. - Boundary markers: None explicitly mentioned in the processing instructions.
- Capability inventory: Access to the
xcsymtool and the local shell environment. - Sanitization: No specific sanitization or validation steps are outlined for the fallback manual parsing logic.
Audit Metadata