hmos-appfreeze-analysis
Pass
Audited by Gen Agent Trust Hub on Jun 22, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill invokes local shell scripts (
scripts/macos/reliability_analyzeandscripts/macos/sample_stack_analyzer) to process log files and sampling stacks. These scripts are used as functional tools within the skill's defined workflow. - [PROMPT_INJECTION]: Indirect Prompt Injection Surface.
- Ingestion points: The skill ingests untrusted data from user-uploaded fault logs and sampling stack files (SKILL.md, Step 1 and Step 8).
- Boundary markers: The instructions do not specify the use of delimiters or 'ignore' instructions to prevent the agent from obeying commands potentially embedded in the log text.
- Capability inventory: The skill possesses the capability to execute subprocesses and generate structured reports based on data interpretation.
- Sanitization: There is no explicit mechanism described to sanitize or validate the content of the logs before processing, which could allow an attacker to craft a log file that influences the agent's diagnostic output.
Audit Metadata